INDEX

Explanations

the superlative form of adjectives for sizes or quantities

oai_token-act-pair · gpt-3.5-turbo

phrases that denote entities recognized as the largest in their respective categories

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

jad

-0.82

fen

-0.78

chy

-0.76

bara

-0.74

Mub

-0.72

rology

-0.72

earth

-0.72

yang

-0.72

neg

-0.72

utenant

-0.71

POSITIVE LOGITS

gest

0.92

(>

0.87

 scale

0.82

 quantities

0.81

 shareholder

0.81

 chunk

0.81

 swath

0.79

 obstacle

0.79

 portion

0.78

 denomination

0.77

Activations Density 0.034%

the superlative form of adjectives for sizes or quantities

phrases that denote entities recognized as the largest in their respective categories

No Comments

No Known Activations