INDEX

Explanations

questions or statements that involve asking or being asked about something, potentially related to discussions or interviews

oai_token-act-pair · gpt-3.5-turbo

phrases that introduce topics or questions in a conversation

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

EStreamFrame

-0.72

Tag

-0.69

readable

-0.69

knit

-0.68

 Rats

-0.67

Block

-0.66

peat

-0.65

Chapter

-0.65

Ã©t

-0.64

Ã©

-0.63

POSITIVE LOGITS

 quizz

0.82

xus

0.70

 anonymity

0.70

 categ

0.67

 postp

0.66

isson

0.65

 constitu

0.64

 sexism

0.64

amera

0.64

 brightness

0.64

Activations Density 0.089%

questions or statements that involve asking or being asked about something, potentially related to discussions or interviews

phrases that introduce topics or questions in a conversation

No Comments

No Known Activations