INDEX

Explanations

placeholders or frequently occurring characters in a technical or coded context

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

numbers and code snippets

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

rrggbb

-0.58

 dAtA

-0.53

 uLocal

-0.51

 NSCoder

-0.48

 Engineered

-0.48

Jîn

-0.46

הערות

-0.45

፩

-0.43

opsida

-0.42

amssymb

-0.41

POSITIVE LOGITS

 nemlig

0.44

intenant

0.41

TintMode

0.39

 nämlich

0.37

 encontraban

0.35

BagLayout

0.35

 bowiem

0.35

 though

0.35

RTSC

0.35

Neither

0.35

Activations Density 0.065%

placeholders or frequently occurring characters in a technical or coded context

numbers and code snippets

No Comments

No Known Activations