INDEX

Explanations

phrases related to specific names or entities, potentially focusing on characters or individuals

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names and brands

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

anooga

-0.80

ovies

-0.76

terson

-0.71

 Corpus

-0.68

gran

-0.67

ascript

-0.67

asia

-0.67

 Lima

-0.66

alion

-0.66

 Hindi

-0.65

POSITIVE LOGITS

senal

1.23

interstitial

0.93

RR

0.88

kefeller

0.82

ussia

0.74

acing

0.73

uling

0.73

eco

0.72

haps

0.71

Activations Density 0.048%

phrases related to specific names or entities, potentially focusing on characters or individuals

proper nouns, specifically names and brands

No Comments

No Known Activations