INDEX

Explanations

phrases related to dates and events mentioned in a specific format ("January 28," etc.), often with additional context provided

oai_token-act-pair · gpt-3.5-turbo

sequences of asterisks commonly used for emphasis or placeholders

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ly

-0.85

liness

-0.77

ilia

-0.72

iveness

-0.71

ugu

-0.67

ively

-0.67

ilic

-0.66

ories

-0.65

ijk

-0.63

 intimid

-0.61

POSITIVE LOGITS

kw

0.91

taboola

0.81

Madison

0.81

orks

0.77

quote

0.77

Discussion

0.75

DER

0.74

Edited

0.72

THIS

0.72

learn

0.71

Activations Density 0.035%

phrases related to dates and events mentioned in a specific format ("January 28," etc.), often with additional context provided

sequences of asterisks commonly used for emphasis or placeholders

No Comments

No Known Activations