INDEX

Explanations

structured references and citations

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

references and external links

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

RegressionTest

-0.46

SequentialGroup

-0.40

ArgumentParser

-0.39

 createSlice

-0.38

VertexAttrib

-0.35

posedge

-0.35

styleType

-0.35

 actionTypes

-0.35

 السيا

-0.34

gonic

-0.33

POSITIVE LOGITS

 kasarigan

0.56

 referenties

0.52

Numerade

0.51

 ddelweddau

0.48

 Hidup

0.48

 Roskov

0.47

ślę

0.45

representative

0.44

Representative

0.44

Expedition

0.43

Activations Density 0.005%

structured references and citations

references and external links

No Comments

No Known Activations