INDEX

Explanations

function return statements in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Tikang

-0.70

lwjgl

-0.65

alisation

-0.57

 margin

-0.54

خول

-0.52

ecker

-0.51

agog

-0.49

 شوید

-0.49

ﬄ

-0.49

urgeon

-0.48

POSITIVE LOGITS

 depth

0.73

 interviews

0.68

 Depth

0.66

 depths

0.65

Cana

0.65

depth

0.63

 recommandée

0.61

 époux

0.59

DataPropertyName

0.59

 profondeur

0.59

Activations Density 0.111%

function return statements in code

No Comments

No Known Activations