INDEX

Explanations

phrases indicating belief, expectation, suspicion, or assumption

oai_token-act-pair · gpt-3.5-turbo

phrases expressing thoughts, beliefs, and expectations

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

srf

-0.73

ortunately

-0.68

ebook

-0.64

 synd

-0.63

flo

-0.63

rawdownloadcloneembedreportprint

-0.63

 subur

-0.62

ÃĥÃĤ

-0.62

 practition

-0.61

adesh

-0.60

POSITIVE LOGITS

enance

1.24

uate

0.85

lement

0.81

peak

0.79

igan

0.70

ANY

0.70

lift

0.69

dress

0.69

ample

0.68

ohn

0.68

Activations Density 0.196%

phrases indicating belief, expectation, suspicion, or assumption

phrases expressing thoughts, beliefs, and expectations

No Comments

No Known Activations