INDEX

Explanations

adjectives describing things in a specific manner

oai_token-act-pair · gpt-3.5-turbo

phrases indicating types or characteristics of things

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

idelines

-0.78

ĸļ

-0.76

alf

-0.74

 CrossRef

-0.74

 Below

-0.71

esses

-0.70

 Beet

-0.69

çīĪ

-0.68

dn

-0.68

heid

-0.67

POSITIVE LOGITS

 thing

1.32

 stuff

0.92

 nonsense

0.84

 crap

0.84

 mentality

0.84

 scenario

0.83

 luck

0.83

 behavior

0.82

guy

0.82

 trauma

0.82

Activations Density 0.051%

adjectives describing things in a specific manner

phrases indicating types or characteristics of things

No Comments

No Known Activations