INDEX

Explanations

phrases enclosed in parentheses

oai_token-act-pair · gpt-3.5-turbo

parentheses and related contextual phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

EStream

-0.84

etheus

-0.70

wagen

-0.67

 Cohn

-0.65

ortium

-0.65

 Keeper

-0.63

izabeth

-0.62

-0.61

 trave

-0.61

utonium

-0.60

POSITIVE LOGITS

sounding

1.15

comings

0.91

notations

0.89

non

0.85

aggressive

0.81

advertising

0.80

ingen

0.74

fixes

0.73

 economical

0.73

albeit

0.73

Activations Density 0.307%

phrases enclosed in parentheses

parentheses and related contextual phrases

No Comments

No Known Activations