INDEX

Explanations

phrases indicating the addition of information or statements by someone

oai_token-act-pair · gpt-3.5-turbo

the phrase "adding" and its frequent usage in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

crow

-0.66

å£«

-0.66

kat

-0.64

DragonMagazine

-0.64

 Kardashian

-0.63

pter

-0.63

arius

-0.62

ograms

-0.61

ogram

-0.61

 Replay

-0.60

POSITIVE LOGITS

ictions

0.89

encies

0.84

 omin

0.82

itionally

0.80

itions

0.78

itious

0.76

itional

0.76

antly

0.72

 inval

0.72

ITION

0.72

Activations Density 0.017%

phrases indicating the addition of information or statements by someone

the phrase "adding" and its frequent usage in context

No Comments

No Known Activations