INDEX

Explanations

words or phrases indicating a choice between two options

oai_token-act-pair · gpt-3.5-turbo

references to binary or dual concepts

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

MSN

-0.76

matter

-0.72

actionDate

-0.68

vic

-0.68

Unt

-0.68

utsche

-0.66

pat

-0.64

zee

-0.64

shed

-0.63

 Spectre

-0.63

POSITIVE LOGITS

 dozen

0.76

 factors

0.74

 quir

0.70

 options

0.68

teenth

0.68

 reasons

0.67

 choices

0.65

 finalists

0.65

 hemisphere

0.65

arios

0.65

Activations Density 0.048%

words or phrases indicating a choice between two options

references to binary or dual concepts

No Comments

No Known Activations