INDEX

Explanations

high-frequency words or phrases that occur in the text

oai_token-act-pair · gpt-3.5-turbo

quantitative expressions and phrases related to approximation

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

IBLE

-0.64

dies

-0.63

 bounty

-0.62

ailable

-0.59

senal

-0.59

CV

-0.58

 debtor

-0.57

 destination

-0.56

jo

-0.56

 graveyard

-0.55

POSITIVE LOGITS

entimes

1.18

 importantly

1.11

withstanding

0.91

etheless

0.89

Ago

0.86

ortunately

0.84

 surprisingly

0.81

 unsurprisingly

0.78

ccording

0.77

surprisingly

0.76

Activations Density 0.212%

high-frequency words or phrases that occur in the text

quantitative expressions and phrases related to approximation

No Comments

No Known Activations