INDEX

Explanations

phrases involving questions or statements about existence or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

Whom

-0.62

Pfalz

-0.60

paksa

-0.57

 tantum

-0.54

BagConstraints

-0.54

 нещо

-0.53

geordnet

-0.52

 enfance

-0.52

איך

-0.51

selves

-0.51

POSITIVE LOGITS

 happening

1.17

 wrong

1.17

wrong

0.82

 Happening

0.80

 Wrong

0.80

 happened

0.79

 WRONG

0.77

 needed

0.73

 missing

0.73

 happen

0.72

Activations Density 0.152%

phrases involving questions or statements about existence or conditions

No Comments

No Known Activations