INDEX

Explanations

references to celebrities or prominent figures

oai_token-act-pair · gpt-3.5-turbo

references to "star" in various contexts, likely relating to notable personalities or features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

»Ĵ

-0.76

ĵĺ

-0.76

channelAvailability

-0.74

ipop

-0.72

odcast

-0.72

ãĥ¼ãĥ³

-0.69

veyard

-0.69

£ı

-0.68

ADRA

-0.67

utics

-0.66

POSITIVE LOGITS

burst

1.02

bucks

0.99

let

0.95

stru

0.91

light

0.90

lets

0.90

liner

0.88

ring

0.87

fish

0.86

rer

0.85

Activations Density 0.022%

references to celebrities or prominent figures

references to "star" in various contexts, likely relating to notable personalities or features

No Comments

No Known Activations