INDEX

Explanations

the word "meant."

oai_token-act-pair · gpt-3.5-turbo

phrases that express intention or purpose

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

SPONSORED

-0.92

anon

-0.75

EStreamFrame

-0.71

âĨĳ

-0.70

ois

-0.68

wine

-0.68

cart

-0.66

redo

-0.65

cence

-0.64

JM

-0.63

POSITIVE LOGITS

terday

0.76

 goodbye

0.73

ERSON

0.68

ivil

0.67

Ðº

0.66

ĸļ

0.66

monton

0.65

romeda

0.65

 spirited

0.64

reprene

0.64

Activations Density 0.018%

the word "meant."

phrases that express intention or purpose

No Comments

No Known Activations