INDEX

Explanations

answers or conclusions in a conversation or text

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

numerical and programming context

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

IsMutable

-0.60

devamını

-0.53

ſammen

-0.52

windowFixed

-0.51

 Савезне

-0.47

 chains

-0.46

 BorderLayout

-0.46

 queſta

-0.45

 nonUne

-0.45

MigrationBuilder

-0.45

POSITIVE LOGITS

 Réponses

0.42

ArgsConstructor

0.37

 nôtre

0.34

 trouw

0.34

SourceChecksum

0.33

 tră

0.32

 answers

0.32

sin

0.32

 mystère

0.31

nommen

0.31

Activations Density 0.000%

answers or conclusions in a conversation or text

numerical and programming context

No Comments

No Known Activations