INDEX

Explanations

names of individuals or entities

oai_token-act-pair · gpt-3.5-turbo

prominent names of individuals mentioned in the context of events or statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

riet

-0.92

raltar

-0.73

ment

-0.65

uttered

-0.64

rica

-0.64

psc

-0.63

rave

-0.62

 Olive

-0.62

BAT

-0.62

arette

-0.61

POSITIVE LOGITS

sembly

0.86

atra

0.80

ners

0.78

uctor

0.76

terday

0.75

numbered

0.74

ivas

0.73

DonaldTrump

0.73

 tomat

0.70

 Sabha

0.70

Activations Density 0.036%

names of individuals or entities

prominent names of individuals mentioned in the context of events or statements

No Comments

No Known Activations