INDEX

Explanations

words related to physical objects and actions

oai_token-act-pair · gpt-3.5-turbo

specific nouns and terms related to various subjects, especially in science, film, and cooking

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

 referen

-0.89

vous

-0.77

arlane

-0.70

 Masquerade

-0.66

ĳå£«

-0.65

 notor

-0.64

ciating

-0.63

 proport

-0.62

 redes

-0.61

Ø§ÙĦ

-0.60

POSITIVE LOGITS

imus

0.79

auts

0.70

rees

0.66

antis

0.66

forest

0.63

nets

0.62

 bush

0.61

lines

0.61

rings

0.60

ombies

0.59

Activations Density 0.465%

words related to physical objects and actions

specific nouns and terms related to various subjects, especially in science, film, and cooking

No Comments

No Known Activations