INDEX

Explanations

phrases related to the interpretation and analysis of data and findings

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

interpreting or understanding findings

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

 autorytatywna

-0.52

windowFixed

-0.46

 BorderSide

-0.46

 întâ

-0.42

ConstraintMaker

-0.40

WriteBarrier

-0.40

PreferredItem

-0.40

 gelijk

-0.39

 LUMP

-0.37

mich

-0.36

POSITIVE LOGITS

 decipher

0.69

 interpreting

0.69

 interpretar

0.68

 Interpreting

0.66

 interpretation

0.66

 interprets

0.66

 decoding

0.63

 interpret

0.63

 INTERPRET

0.61

interpretation

0.59

Activations Density 0.041%

phrases related to the interpretation and analysis of data and findings

interpreting or understanding findings

No Comments

No Known Activations