INDEX

Explanations

locations and specific features within a setting

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

locations and places

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

 otomatig

-0.39

 negativ

-0.38

 fraught

-0.38

ggiamento

-0.36

ypeł

-0.35

ⓧ

-0.35

 bassi

-0.34

 grossesse

-0.34

 aparente

-0.34

 '\\;'

-0.33

POSITIVE LOGITS

quelize

0.53

ReusableCell

0.52

StoryboardSegue

0.51

verifyException

0.51

帖最后由

0.50

CPtr

0.49

 AssemblyProduct

0.47

mappedBy

0.47

ynomial

0.47

setopt

0.46

Activations Density 0.006%

locations and specific features within a setting

locations and places

No Comments

No Known Activations