INDEX

Explanations

structured data definitions and mappings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

oredCriteria

-0.88

SharedCtor

-0.78

AutoScaleMode

-0.69

bootstrapcdn

-0.64

RegressionTest

-0.63

fromnode

-0.61

 químicas

-0.61

 GenerationType

-0.60

Revenir

-0.60

 africains

-0.59

POSITIVE LOGITS

ptid

0.53

ыгана

0.53

()]);

0.52

eper

0.49

%";

0.48

ranger

0.48

WillAppear

0.48

hurst

0.48

splitContainer

0.48

IMPORTED

0.48

Activations Density 0.085%

structured data definitions and mappings

No Comments

No Known Activations