INDEX

Explanations

phrases indicating readiness and preparation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

Geografia

-0.55

JNIEnv

-0.53

WriteLiteral

-0.53

middot

-0.52

UnusedPrivate

-0.48

Detalhes

-0.48

ifera

-0.47

amaño

-0.47

DMETHOD

-0.47

cian

-0.47

POSITIVE LOGITS

made

0.79

IsMutable

0.73

FunctionFlags

0.73

 sàng

0.61

 sedia

0.60

willi

0.60

 sẵn

0.60

teady

0.57

好在

0.57

 prête

0.57

Activations Density 0.105%

phrases indicating readiness and preparation

No Comments

No Known Activations