INDEX

Explanations

phrases indicating causation or potential consequences

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "lead" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Mach

-0.76

apy

-0.73

eatures

-0.66

ongyang

-0.65

emis

-0.63

arma

-0.63

cube

-0.63

phis

-0.63

orrow

-0.62

ategor

-0.62

POSITIVE LOGITS

lead

1.05

 lead

0.90

better

0.88

 Lead

0.85

 Leading

0.81

Lead

0.81

 leads

0.75

 leading

0.71

boards

0.70

ership

0.70

Activations Density 0.019%

phrases indicating causation or potential consequences

occurrences of the word "lead" in various contexts

No Comments

No Known Activations