INDEX

Explanations

syntax elements and function definitions within code snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 Meksiku

-0.71

 nonatomic

-0.64

Clik

-0.63

 bacio

-0.63

клопе

-0.63

 BigNumber

-0.58

 jScrollPane

-0.58

 تضيفلها

-0.57

tagHelperRunner

-0.56

jwa

-0.53

POSITIVE LOGITS

 Teufel

0.72

 mwenye

0.72

مراجع

0.68

haustible

0.59

 débuts

0.59

ismic

0.58

 victimes

0.58

 miele

0.57

 مرک

0.56

==""){

0.54

Activations Density 0.165%

syntax elements and function definitions within code snippets

No Comments

No Known Activations