INDEX

Explanations

quantitative statistics or percentages relating to various topics

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

chanind/openwebtext-gemma

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

ctigges/openwebtext-gemma-1024-cl

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

<bos>

-2.75

 intersper

-1.37

ⓧ

-1.16

 disbur

-0.95

-0.94

 encomp

-0.93

/**

-0.91

 overcrow

-0.91

 rouse

-0.90

 reconno

-0.89

POSITIVE LOGITS

 kafe

0.73

 kristal

0.71

 karton

0.68

 silikon

0.66

0.64

 mikrofon

0.63

 jawa

0.63

 panik

0.62

 antik

0.62

 keramik

0.62

Activations Density 0.086%

quantitative statistics or percentages relating to various topics

No Known Activations