INDEX

Explanations

phrases indicating a recurring or repetitive action

oai_token-act-pair · gpt-3.5-turbo

the repetition of the word "each."

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

tops

-0.78

dn

-0.76

stones

-0.73

abs

-0.70

rovers

-0.68

Chain

-0.68

bows

-0.68

children

-0.66

haven

-0.66

nit

-0.65

POSITIVE LOGITS

 successive

1.20

 iteration

0.89

where

0.87

 individual

0.86

 participant

0.81

 weekday

0.80

 subsequent

0.78

 person

0.78

 individually

0.77

 ounce

0.77

Activations Density 0.039%

phrases indicating a recurring or repetitive action

the repetition of the word "each."

No Comments

No Known Activations