INDEX

Explanations

structures related to variable definitions and assignments in mathematical or programming contexts

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

Let followed by variable

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

󠁣

-0.62

+#+

-0.60

 ModelExpression

-0.59

 Administrativna

-0.59

Tikang

-0.56

}{@

-0.54

ngrx

-0.52

 BERNAMA

-0.50

ImageContext

-0.49

imageshack

-0.48

POSITIVE LOGITS

Референце

0.47

me

0.40

given

0.38

two

0.38

 data

0.36

 sebuah

0.35

us

0.34

ditionally

0.34

 Given

0.34

Activations Density 0.026%

structures related to variable definitions and assignments in mathematical or programming contexts

Let followed by variable

No Comments

No Known Activations