INDEX

Explanations

terms related to files and documents

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

documents

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

strix

-0.39

Leggi

-0.35

 many

-0.32

stretchr

-0.32

]='\

-0.31

mbalikan

-0.30

 vielen

-0.30

Abraço

-0.30

(&:

-0.30

 returning

-0.29

POSITIVE LOGITS

Documents

1.57

 Documents

1.35

documents

1.23

 documents

1.23

 Document

1.11

 DOCUMENTS

1.10

Document

1.10

 document

1.01

document

0.97

 Dokumente

0.94

Activations Density 0.000%

terms related to files and documents

documents

No Comments

No Known Activations