INDEX

Explanations

references to document structure and metadata

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

academic & technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

 الحره

-0.59

 怎样

-0.54

 iconLine

-0.47

Diweddarwch

-0.47

المناصب

-0.46

 تضيفلها

-0.45

findpost

-0.42

hoeddwyd

-0.41

 deals

-0.41

 didst

-0.40

POSITIVE LOGITS

MessageTagHelper

0.53

verifyException

0.52

awtextra

0.49

 consultato

0.47

summary

0.41

."

0.39

 ModelRenderer

0.39

(©

0.38

PreInfinity

0.38

setVerticalGroup

0.38

Activations Density 0.186%

references to document structure and metadata

academic & technical contexts

No Comments

No Known Activations