INDEX

Explanations

phrases indicating the occurrence or arrival of events

oai_token-act-pair · gpt-3.5-turbo

the word "in" along with various contexts indicating its frequency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

DOM

-0.75

emis

-0.72

STER

-0.70

cas

-0.63

fac

-0.62

ucc

-0.61

 Talent

-0.61

sworth

-0.60

ICO

-0.60

iveness

-0.59

POSITIVE LOGITS

 handy

1.45

 contact

0.92

 leaps

0.88

escap

0.84

dro

0.80

 response

0.76

 conjunction

0.76

 waves

0.75

 succession

0.75

 tandem

0.74

Activations Density 0.061%

phrases indicating the occurrence or arrival of events

the word "in" along with various contexts indicating its frequency

No Comments

No Known Activations