INDEX

Explanations

proper nouns related to the term "Hur"

oai_token-act-pair · gpt-3.5-turbo

references to the word "Hur" 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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Skydragon

-0.80

ä»£

-0.77

nesota

-0.76

ħĭ

-0.73

ancial

-0.71

é¾įå¥ĳå£«

-0.71

ynthesis

-0.70

istration

-0.70

ãĤ´ãĥ³

-0.68

holders

-0.67

POSITIVE LOGITS

witz

0.91

ving

0.89

acan

0.87

ley

0.87

ves

0.87

ricane

0.85

ricanes

0.85

rah

0.79

few

0.77

rier

0.75

Activations Density 0.007%

proper nouns related to the term "Hur"

references to the word "Hur" in various contexts

No Comments

No Known Activations