INDEX

Explanations

references to figures and mathematical expressions

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

 navide

-0.80

 cromado

-0.79

 temporales

-0.79

 démocr

-0.78

 Económica

-0.75

 européennes

-0.75

 imidlertid

-0.73

 groote

-0.73

 vanske

-0.73

 inferiores

-0.73

POSITIVE LOGITS

 defaultstate

0.53

wh

0.51

ⓧ

0.49

whe

0.49

fin

0.49

Fin

0.49

Wh

0.49

क

0.49

ane

0.47

OGND

0.47

Activations Density 0.126%

references to figures and mathematical expressions

No Comments

No Known Activations