INDEX

Explanations

references to tubes in various contexts

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

 plan

-0.59

 plans

-0.55

acij

-0.54

quillas

-0.54

กระท

-0.54

“……

-0.53

/');

-0.53

 chodzi

-0.53

 organization

-0.52

 perdon

-0.51

POSITIVE LOGITS

脚注の使い方

0.83

 AssemblyCulture

0.80

 INTO

0.76

OGND

0.76

 समीक्षक

0.75

 Himo

0.73

 الحره

0.73

ArrowToggle

0.70

ellido

0.69

Into

0.68

Activations Density 0.147%

references to tubes in various contexts

No Comments

No Known Activations