INDEX

Explanations

references to burgers

oai_token-act-pair · gpt-3.5-turbo

references to burgers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

agnetic

-0.84

oral

-0.76

inel

-0.75

 Emin

-0.69

agall

-0.69

uchin

-0.68

 Atmospheric

-0.68

nces

-0.67

eus

-0.66

 Soros

-0.66

POSITIVE LOGITS

 burger

0.87

 burgers

0.86

 emoji

0.85

meat

0.83

urger

0.82

 steak

0.81

 hamb

0.81

bowl

0.80

becue

0.79

balls

0.78

Activations Density 0.040%

references to burgers

references to burgers

No Comments

No Known Activations