INDEX

Explanations

references to programming elements and user interface components

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

UI components

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

 myſelf

-0.49

AddTagHelper

-0.46

featureID

-0.44

CodeAttribute

-0.43

 &___

-0.43

 Privacidade

-0.43

 preſent

-0.42

rungsseite

-0.42

SharedDtor

-0.42

 defaultstate

-0.41

POSITIVE LOGITS

ViewImports

0.42

 settlement

0.42

uxxxx

0.40

pri

0.39

mintaan

0.39

bazel

0.38

 rotina

0.38

dis

0.36

 stability

0.35

цездатний

0.35

Activations Density 0.041%

references to programming elements and user interface components

UI components

No Comments

No Known Activations

references to programming elements and user interface components

UI components

No Comments

No Known Activations