INDEX

Explanations

references to data processing components in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

CrossRef

-0.63

مصادر

-0.61

ModelForm

-0.57

 оригіналу

-0.56

 kaynağından

-0.56

sidemargin

-0.51

iffa

-0.49

日閲覧

-0.49

viti

-0.49

 ModelExpression

-0.48

POSITIVE LOGITS

 <=",

0.56

guard

0.54

ismic

0.50

sière

0.49

Guard

0.48

 guard

0.48

 Guards

0.48

 OMITBAD

0.46

 Guard

0.45

 незавершена

0.45

Activations Density 0.125%

references to data processing components in a programming context

No Comments

No Known Activations