INDEX

Explanations

movie titles or proper nouns

oai_token-act-pair · gpt-3.5-turbo

words and phrases related to film and ratings

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 disruption

-0.70

 Disclosure

-0.68

NR

-0.66

NX

-0.66

 Dalai

-0.63

 Coord

-0.61

 closure

-0.61

 Explain

-0.61

LTD

-0.59

 closures

-0.59

POSITIVE LOGITS

otten

3.49

ween

2.84

 stra

1.65

uries

1.33

ippi

1.09

pload

0.94

ingen

0.93

seless

0.91

ulp

0.88

ixt

0.87

Activations Density 0.033%

movie titles or proper nouns

words and phrases related to film and ratings

No Comments

No Known Activations