INDEX

Explanations

references to sources or citations

oai_token-act-pair · gpt-3.5-turbo

references to reputable sources of information

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

aeper

-0.69

TAG

-0.66

oos

-0.66

Ħ¢

-0.64

boxing

-0.64

otos

-0.63

roe

-0.62

olded

-0.61

STRUCT

-0.60

âĶģ

-0.59

POSITIVE LOGITS

ources

1.19

ourcing

1.16

 sources

1.09

 Sources

1.01

etter

1.01

ourced

0.93

afe

0.92

cale

0.88

 consulted

0.87

hips

0.86

Activations Density 0.040%

references to sources or citations

references to reputable sources of information

No Comments

No Known Activations