INDEX

Explanations

the introduction and categorization of lists or groups of related items or information

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

listing items

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

 level

-0.28

etc

-0.28

 response

-0.27

was

-0.27

 activity

-0.27

好

-0.26

 Keim

-0.26

llvm

-0.26

 intervention

-0.26

 attention

-0.26

POSITIVE LOGITS

ConstraintMaker

0.84

ftagPool

0.80

 müſſen

0.75

iſchen

0.73

 queſta

0.73

 dieſes

0.73

fjspx

0.72

 ſeinen

0.72

niſſe

0.71

iſche

0.71

Activations Density 0.044%

the introduction and categorization of lists or groups of related items or information

listing items

No Comments

No Known Activations