INDEX

Explanations

mentions of specific names

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals or brands, particularly 'Goodman' and 'Mustang'

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

tymology

-0.96

ples

-0.93

 mathemat

-0.84

rences

-0.83

 livest

-0.82

uters

-0.80

ces

-0.75

ħ

-0.74

ury

-0.74

 contracting

-0.73

POSITIVE LOGITS

Adds

0.69

eyes

0.68

Feel

0.67

DERR

0.67

 Beirut

0.67

 ãĤµ

0.66

SIGN

0.64

ollen

0.63

UX

0.63

ðŁĺ

0.63

Activations Density 0.069%

mentions of specific names

references to specific individuals or brands, particularly 'Goodman' and 'Mustang'

No Comments

No Known Activations