INDEX

Explanations

references to functions and methods in programming code

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

Code snippets with brackets/parentheses

np_acts-logits-general · gemini-2.0-flash

submit all records

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Життєпис

-0.51

lottes

-0.47

رشف

-0.47

Referencies

-0.46

licata

-0.46

 KeyError

-0.45

DRM

-0.45

Kino

-0.44

cheibe

-0.44

Certificate

-0.43

POSITIVE LOGITS

DockStyle

0.45

rawDesc

0.40

 temporarily

0.39

 ModelExpression

0.36

InputBorder

0.33

Gruss

0.32

bitField

0.31

 answer

0.29

nh

0.29

 temporary

0.29

Activations Density 0.251%

references to functions and methods in programming code

Code snippets with brackets/parentheses

submit all records

No Comments

No Known Activations