INDEX

Explanations

phrases indicating someone or something being specifically highlighted or targeted

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "singled out."

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

veyard

-0.73

ipeg

-0.71

istor

-0.71

 upkeep

-0.66

issance

-0.65

anos

-0.64

 embr

-0.63

emi

-0.63

anwhile

-0.62

 liaison

-0.61

POSITIVE LOGITS

 è£ıè

0.85

 exceptions

0.77

Reason

0.72

posts

0.67

IFIED

0.65

 criteria

0.65

STDOUT

0.65

ãĤī

0.64

 Exception

0.64

Section

0.64

Activations Density 0.035%

phrases indicating someone or something being specifically highlighted or targeted

instances of the phrase "singled out."

No Comments

No Known Activations