INDEX

Explanations

names of people or entities

oai_token-act-pair · gpt-3.5-turbo

specific keywords related to events or locations

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

DragonMagazine

-0.73

NPR

-0.68

 vested

-0.65

poll

-0.62

 facult

-0.62

posted

-0.59

 psychiat

-0.59

izoph

-0.59

 sacrific

-0.57

Emb

-0.56

POSITIVE LOGITS

arella

0.84

zees

0.79

cular

0.79

ller

0.75

akeru

0.74

hof

0.68

ufact

0.67

acht

0.66

zee

0.65

utics

0.65

Activations Density 0.471%

names of people or entities

specific keywords related to events or locations

No Comments

No Known Activations