INDEX

Explanations

proper nouns related to names of individuals

oai_token-act-pair · gpt-3.5-turbo

occurrences of specific names and terms related to individuals and biological concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

iop

-0.77

 Seym

-0.77

entric

-0.73

icals

-0.73

ulence

-0.73

ilities

-0.72

iotic

-0.72

arro

-0.71

inelli

-0.70

ioch

-0.69

POSITIVE LOGITS

ering

0.78

cest

0.73

peak

0.73

ãĥ³ãĤ¸

0.71

ende

0.71

erers

0.70

dfx

0.70

ŃĶ

0.69

 quarters

0.69

ulic

0.68

Activations Density 0.023%

proper nouns related to names of individuals

occurrences of specific names and terms related to individuals and biological concepts

No Comments

No Known Activations