INDEX

Explanations

references to help, support, resources, and documentation within educational or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ReactDOM

-0.56

таратура

-0.51

kì

-0.51

簧

-0.47

Portály

-0.46

̍t

-0.45

 líquidos

-0.45

 kỳ

-0.44

綜合報導

-0.44

gnore

-0.43

POSITIVE LOGITS

rungsseite

0.71

PreferredItem

0.69

 breakdowns

0.66

 fhort

0.63

 noten

0.63

 raiſ

0.63

avadoc

0.61

 BoxFit

0.61

 myſelf

0.61

 مشين

0.61

Activations Density 0.609%

references to help, support, resources, and documentation within educational or technical contexts

No Comments

No Known Activations