INDEX

Explanations

formatting for documents and coding snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

protoimpl

-0.87

AndEndTag

-0.77

>>;

-0.75

SourceChecksum

-0.73

IntoConstraints

-0.73

 uncomment

-0.72

artifactId

-0.72

ⓘ

-0.72

StoryboardSegue

-0.71

 ModelExpression

-0.71

POSITIVE LOGITS

 المعيارى

0.56

 pherom

0.48

 Geschle

0.48

lasma

0.46

itinéraire

0.45

číta

0.45

mathrm

0.43

 debent

0.43

GEBURTS

0.43

↵↵

0.43

Activations Density 0.013%

formatting for documents and coding snippets

No Comments

No Known Activations