INDEX

Explanations

names of individuals and prominent figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

EndGlobalSection

-0.81

 kasarigan

-0.81

qrstuvwxyz

-0.69

AutoScaleMode

-0.65

GEBURTSDATUM

-0.63

+#+#

-0.63

 propOrder

-0.62

SharedCtor

-0.61

 мәкал

-0.61

IntoConstraints

-0.61

POSITIVE LOGITS

0.91

’

0.88

 himſelf

0.85

 myſelf

0.74

 Theſe

0.66

ův

0.65

 stesso

0.62

 becauſe

0.61

 ſaid

0.59

 leaſt

0.59

Activations Density 0.357%

names of individuals and prominent figures

No Comments

No Known Activations