INDEX

Explanations

references to academic papers or research articles

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

a "paper"

np_acts-logits-general · gemini-2.0-flash

the word paper

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

MergeFrom

-0.61

nect

-0.47

stalgia

-0.47

liferay

-0.46

quint

-0.46

mighty

-0.46

Lynx

-0.45

 Roskov

-0.44

swt

-0.44

Quint

-0.43

POSITIVE LOGITS

 paper

2.45

Paper

2.25

 Paper

2.25

paper

2.19

 PAPER

2.14

 papers

1.99

PAPER

1.98

 Papers

1.87

Papers

1.77

papers

1.76

Activations Density 0.119%

references to academic papers or research articles

a "paper"

the word paper

No Comments

No Known Activations