INDEX

Explanations

keywords related to programming constructs and error handling

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

 particular

-0.69

 Track

-0.56

chowa

-0.56

省市镇

-0.52

cedido

-0.51

 corre

-0.49

 particularly

-0.49

 Hepburn

-0.49

WebElementEntity

-0.49

terus

-0.49

POSITIVE LOGITS

DockStyle

0.76

 familières

0.70

ViewImports

0.70

cla

0.70

ModelAdmin

0.68

cl

0.66

 dépens

0.66

 Specials

0.66

Alike

0.65

logo

0.64

Activations Density 0.095%

keywords related to programming constructs and error handling

No Comments

No Known Activations