INDEX

Explanations

mentions of furniture, specifically couches and sofas

oai_token-act-pair · gpt-3.5-turbo

references to couches and sofas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

uality

-0.71

utenberg

-0.68

 Abel

-0.67

 Morse

-0.66

 hypers

-0.66

REDACTED

-0.65

heny

-0.63

 Ames

-0.62

Uz

-0.62

eters

-0.62

POSITIVE LOGITS

 cush

1.25

 cushion

1.11

 sofa

0.95

washer

0.95

tops

0.93

 mattress

0.93

estinal

0.85

 couch

0.85

visor

0.85

chair

0.85

Activations Density 0.027%

mentions of furniture, specifically couches and sofas

references to couches and sofas

No Comments

No Known Activations