INDEX

Explanations

technical terms and code-related keywords

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

adona

-0.64

 greateſt

-0.64

 Stron

-0.59

 Vols

-0.55

Zon

-0.54

حياته

-0.54

 octo

-0.53

 Dost

-0.52

Ush

-0.51

.$$

-0.51

POSITIVE LOGITS

Pyx

0.77

tvguidetime

0.75

 виправивши

0.71

oredCriteria

0.59

absorbing

0.58

VERBOSE

0.56

 României

0.56

 Nathan

0.56

 Vám

0.55

 chiff

0.54

Activations Density 2.713%

technical terms and code-related keywords

No Comments

No Known Activations