INDEX

Explanations

symbols or terms related to mathematical or logical representations, particularly involving set notation or variables

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

empty and ø character

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

documentclass

-0.42

 Smol

-0.42

gql

-0.41

 cref

-0.40

Cio

-0.39

 impati

-0.38

 Creatures

-0.37

,:,

-0.37

lö

-0.36

 nors

-0.36

POSITIVE LOGITS

ö

1.14

Ö

0.91

ø

0.87

Ø

0.73

OA

0.65

TokenNameDOT

0.64

 öde

0.58

Oro

0.57

 Southgate

0.56

yakarta

0.54

Activations Density 0.004%

symbols or terms related to mathematical or logical representations, particularly involving set notation or variables

empty and ø character

No Comments

No Known Activations