INDEX

Explanations

punctuation marks and symbols indicating assignments or operations in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 fusca

-0.70

 onAnimation

-0.65

 înc

-0.59

 Händen

-0.57

 OnInit

-0.57

 fhall

-0.56

woff

-0.55

 setw

-0.55

 ſhall

-0.54

 tracts

-0.54

POSITIVE LOGITS

enderror

0.75

 else

0.75

enumi

0.73

 OTHERWISE

0.69

else

0.69

otherwise

0.68

SpringBootTest

0.65

 Otherwise

0.63

IntoConstraints

0.62

\}\\

0.62

Activations Density 0.031%

punctuation marks and symbols indicating assignments or operations in a programming context

No Comments

No Known Activations