INDEX

Explanations

expressions in a mathematical or technical context, specifically related to symbols and formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

leich

-0.59

yarnpkg

-0.58

rawDesc

-0.54

éb

-0.54

SharedDtor

-0.53

currentColor

-0.52

oneofs

-0.51

cokinetics

-0.51

 segn

-0.50

 Salve

-0.50

POSITIVE LOGITS

<sup>

1.56

<sub>

1.14

<u>

0.94

<em>

0.83

<i>

0.78

 AssemblyTitle

0.71

 }^{\

0.71

<code>

0.70

tfrac

0.68

${

0.66

Activations Density 0.314%

expressions in a mathematical or technical context, specifically related to symbols and formatting

No Comments

No Known Activations