INDEX

Explanations

phrases containing a specific keyword or subject for discussion

oai_token-act-pair · gpt-3.5-turbo

references to abstract concepts or generalizations

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

Lear

-0.77

Reloaded

-0.71

 lapt

-0.69

spo

-0.69

 spoil

-0.64

å¤©

-0.61

Bul

-0.61

Break

-0.61

RM

-0.61

Prosecut

-0.60

POSITIVE LOGITS

 respectively

0.96

rities

0.86

ftime

0.80

ulhu

0.71

reen

0.68

mology

0.68

ulas

0.65

uates

0.65

ums

0.64

imilation

0.64

Activations Density 0.990%

phrases containing a specific keyword or subject for discussion

references to abstract concepts or generalizations

No Comments

No Known Activations