INDEX

Explanations

code-related terms and functions used in programming, particularly in connection with imports, class titles, and object states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 виправивши

-0.51

AutoScaleMode

-0.51

 varmt

-0.48

ifolium

-0.48

 frecuencia

-0.46

 szí

-0.45

smoking

-0.45

 últimos

-0.44

 Einzel

-0.43

ELTS

-0.43

POSITIVE LOGITS

BufferException

0.82

IVEREF

0.77

 Италијани

0.77

LookAnd

0.72

 للاسماء

0.71

enumi

0.68

󠁢

0.65

%";

0.64

RenderAtEndOf

0.64

 ***!

0.63

Activations Density 0.546%

code-related terms and functions used in programming, particularly in connection with imports, class titles, and object states

No Comments

No Known Activations