INDEX

Explanations

references to assistance or support resources

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

help desk and documentation

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

keyColumn

-0.47

aspectj

-0.47

دانشنامهٔ

-0.45

IntoConstraints

-0.44

getJSONArray

-0.44

 PyTuple

-0.40

dafx

-0.40

ieteur

-0.40

 屋根

-0.40

 createSlice

-0.40

POSITIVE LOGITS

desk

0.64

เหลือ

0.63

fully

0.62

 đỡ

0.60

 Helf

0.54

ValueStyle

0.53

help

0.52

 Hilfs

0.49

helps

0.49

helped

0.49

Activations Density 0.041%

references to assistance or support resources

help desk and documentation

No Comments

No Known Activations