INDEX

Explanations

comment syntax across different programming languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TokenNameLPAREN

-0.62

로그램

-0.58

nestjs

-0.57

 useDispatch

-0.56

SuspendLayout

-0.56

Према

-0.53

!("{}",

-0.53

μί

-0.52

 Martel

-0.52

Öffnungszeiten

-0.52

POSITIVE LOGITS



1.04

RegressionTest

0.69

<<<<<<<

0.66

Hochspringen

0.62

تقاوى

0.61

henswürdigkeiten

0.61

prüche

0.60

uxxxx

0.60

رشف

0.58

 converti

0.57

Activations Density 0.074%

comment syntax across different programming languages

No Comments

No Known Activations