INDEX

Explanations

locations or positions within a setting

oai_token-act-pair · gpt-3.5-turbo

instances of punctuation, particularly commas

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

©

-0.79

¤

-0.76

FP

-0.74

UF

-0.74

¸

-0.74

omics

-0.73

usterity

-0.71

ulz

-0.71

eus

-0.70

¯

-0.68

POSITIVE LOGITS

 whence

0.93

 grinning

0.91

 lest

0.89

 albeit

0.88

 flanked

0.85

 shouting

0.83

 preferably

0.81

 soaking

0.81

 clutching

0.80

 whispering

0.79

Activations Density 0.470%

locations or positions within a setting

instances of punctuation, particularly commas

No Comments

No Known Activations