INDEX

Explanations

elements related to significant events or recognitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 ervan

-0.59

 thereupon

-0.59

InjectAttribute

-0.58

 içeris

-0.57

UrlResolution

-0.56

uxxxx

-0.56

merksam

-0.55

jenigen

-0.54

ditionally

-0.54

 consequently

-0.53

POSITIVE LOGITS

rungsseite

0.59

 odkazy

0.57

GOP

0.57

 GenerationType

0.56

Tikang

0.56

但不

0.52

 pode

0.52

‘

0.52

 govt

0.51

 seeks

0.50

Activations Density 0.137%

elements related to significant events or recognitions

No Comments

No Known Activations