INDEX

Explanations

numeric identifiers or references in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

IVEREF

-1.02

DockStyle

-0.79

RenderAtEndOf

-0.78

endcsname

-0.78

mybatisplus

-0.73

 crdi

-0.72

LookAnd

-0.72

NewGuid

-0.70

ftagPool

-0.70

 unknownFields

-0.69

POSITIVE LOGITS

enumi

0.57

MENAFN

0.55

qu

0.49

 figure

0.48

nameof

0.47

 inclusion

0.44

 menak

0.43

rie

0.43

ext

0.43

Qu

0.43

Activations Density 0.022%

numeric identifiers or references in the text

No Comments

No Known Activations