INDEX

Explanations

occurrences of the word "a"

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

this is a

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

SourceChecksum

-0.53

 <<<<<<<<<<<<<<

-0.47

 disambiguazione

-0.46

hoeddwyd

-0.46

 Italijanski

-0.45

sidemargin

-0.44

windowFixed

-0.44

 mergeFrom

-0.44

 الرياضيه

-0.44

 ComVisible

-0.44

POSITIVE LOGITS

 question

0.58

 questions

0.54

 game

0.52

 theory

0.50

 simple

0.48

rog

0.48

 smut

0.48

 bird

0.46

issy

0.46

 Wander

0.46

Activations Density 0.010%

occurrences of the word "a"

this is a

No Comments

No Known Activations