INDEX

Explanations

names of individuals involved in a news story or scandal

oai_token-act-pair · gpt-3.5-turbo

mentions of specific individuals, particularly those involved in a scandal

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

inth

-0.77

ãĤ©

-0.73

dinand

-0.72

ALLY

-0.71

ãĥ¤

-0.70

Ð´

-0.69

*/(

-0.69

eer

-0.69

ICS

-0.68

nesota

-0.68

POSITIVE LOGITS

 Duffy

0.79

 Chow

0.65

igger

0.64

dry

0.64

enhagen

0.64

wig

0.64

 Races

0.64

cake

0.62

 itching

0.62

orks

0.61

Activations Density 0.014%

names of individuals involved in a news story or scandal

mentions of specific individuals, particularly those involved in a scandal

No Comments

No Known Activations