INDEX

Explanations

phrases related to superlatives or emphasis

oai_token-act-pair · gpt-3.5-turbo

phrases indicating significance or prominence

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

Negative Logits

ttes

-0.80

ences

-0.77

heid

-0.73

schild

-0.71

manship

-0.70

jad

-0.69

ious

-0.69

aven

-0.69

ENC

-0.68

mint

-0.67

POSITIVE LOGITS

gest

0.96

 bang

0.91

 obstacle

0.86

 culprit

0.86

 hurdle

0.84

 proponent

0.82

 chunk

0.79

 losers

0.78

oted

0.78

 loser

0.78

Activations Density 0.026%

phrases related to superlatives or emphasis

phrases indicating significance or prominence

No Known Activations