INDEX

Explanations

specific references or citations within a text

oai_token-act-pair · gpt-3.5-turbo

references to citing sources or evidence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

orld

-0.70

ascript

-0.69

ipeg

-0.68

ixtape

-0.66

cum

-0.66

olen

-0.65

cas

-0.65

hattan

-0.65

cos

-0.64

quer

-0.64

POSITIVE LOGITS

 citations

0.96

 citation

0.88

enza

0.86

 quotes

0.80

 cite

0.80

 warnings

0.80

âĨĳ

0.79

 cited

0.78

 citing

0.77

="#

0.75

Activations Density 0.022%

specific references or citations within a text

references to citing sources or evidence

No Comments

No Known Activations