INDEX

Explanations

terms related to authoritative statements or instructions

oai_token-act-pair · gpt-3.5-turbo

statements or phrases that express strong claims or assertions

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

],"

-0.60

)",

-0.58

javascript

-0.54

"—

-0.54

SPONSORED

-0.52

umbn

-0.52

"),

-0.52

 ÂŃ

-0.52

")

-0.49

 Shutterstock

-0.49

POSITIVE LOGITS

cknowled

0.70

oret

0.70

ONSORED

0.64

itialized

0.59

neath

0.58

APTER

0.54

eday

0.54

resy

0.53

 Stupid

0.53

 consequence

0.53

Activations Density 0.799%

terms related to authoritative statements or instructions

statements or phrases that express strong claims or assertions

No Comments

No Known Activations