INDEX

Explanations

names of specific people or entities

oai_token-act-pair · gpt-3.5-turbo

names, places, or entities associated with specific individuals or events

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.62

ASP

-0.60

 DISTR

-0.54

 âĢº

-0.53

 Morty

-0.53

 CONTR

-0.52

taboola

-0.52

 antim

-0.51

 passer

-0.51

 neurot

-0.51

POSITIVE LOGITS

ÃŃn

0.76

ese

0.69

haus

0.65

Ã«

0.64

agate

0.63

eus

0.62

illus

0.62

edi

0.62

unia

0.62

ghan

0.61

Activations Density 0.524%

names of specific people or entities

names, places, or entities associated with specific individuals or events

No Comments

No Known Activations