INDEX

Explanations

programming functions and their definitions

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

anonymous function definitions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

Yesterday

-0.35

 monopo

-0.33

 renseignements

-0.32

 hanem

-0.32

 surtout

-0.32

 dermed

-0.31

 соответственно

-0.31

iertamente

-0.31

 Allerdings

-0.30

 Exteriores

-0.30

POSITIVE LOGITS

orElseThrow

0.76

出版年

0.74

SourceChecksum

0.71

 تضيفلها

0.67

 otomatig

0.66

 EconPapers

0.63

makeConstraints

0.62

:^(

0.60

writeFieldEnd

0.59

 يتيمه

0.58

Activations Density 0.002%

programming functions and their definitions

anonymous function definitions

No Comments

No Known Activations