INDEX

Explanations

specific identifiers or acronyms often associated with a technical or scientific context

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

two-letter acronyms ending in i

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

hbs

-0.31

efois

-0.31

devServer

-0.31

évaluateur

-0.30

<eos>

-0.30

ルター

-0.29

vese

-0.29

ựu

-0.28

udnio

-0.28

 meny

-0.28

POSITIVE LOGITS

EI

0.89

OI

0.77

TSI

0.75

SDI

0.75

SDI

0.75

OI

0.75

QI

0.74

CI

0.73

CI

0.73

SSI

0.73

Activations Density 0.312%

specific identifiers or acronyms often associated with a technical or scientific context

two-letter acronyms ending in i

No Comments

No Known Activations