INDEX

Explanations

Keywords related to newness or recent changes

oai_token-act-pair · gpt-3.5-turbo

references to new policies or changes in governance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Zip

-0.76

uddin

-0.76

aminer

-0.75

ashtra

-0.74

acebook

-0.64

lua

-0.63

itta

-0.63

 Trap

-0.63

ppe

-0.62

 Strauss

-0.61

POSITIVE LOGITS

bies

1.12

bie

1.11

foundland

1.03

 arrivals

1.03

 additions

0.95

 entrants

0.91

 Zealand

0.90

 developments

0.89

 YORK

0.81

 discoveries

0.80

Activations Density 0.107%

Keywords related to newness or recent changes

references to new policies or changes in governance

No Comments

No Known Activations