INDEX

Explanations

references to geometrical shapes and their characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 thirds

-0.61

ględ

-0.59

 fotografico

-0.54

CloseOperation

-0.53

archiviato

-0.53

--)

-0.52

--){

-0.51

substituted

-0.50

RUnlock

-0.49

 martes

-0.49

POSITIVE LOGITS

shapes

1.01

 shapes

0.97

 SHAPE

0.97

Shapes

0.96

 Shapes

0.96

SHAPE

0.89

 Shape

0.80

 shape

0.76

hift

0.73

 calendriers

0.73

Activations Density 0.106%

references to geometrical shapes and their characteristics

No Comments

No Known Activations