INDEX

Explanations

mathematical or programming constructs related to constraints and their definitions in a structured format

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

direction and constraint

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

 initComponents

-0.59

PropertyChanging

-0.52

AddTagHelper

-0.52

новниш

-0.51

 kasarigan

-0.50

DockStyle

-0.50

sizeCache

-0.50

 Differentiation

-0.45

 ilustracja

-0.45

 dál

-0.45

POSITIVE LOGITS

Dragged

0.38

 dump

0.34

 fire

0.33

 Constraint

0.33

 dile

0.33

 Banner

0.31

Dump

0.31

 Oden

0.31

package

0.30

MessageTagHelper

0.30

Activations Density 0.001%

mathematical or programming constructs related to constraints and their definitions in a structured format

direction and constraint

No Comments

No Known Activations