INDEX

Explanations

references to vague or unspecified items

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

stuff and stuffing

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

Negative Logits

nebago

-0.51

 pingente

-0.45

geber

-0.44

 Renal

-0.43

󠁿

-0.43

 Toxicological

-0.41

webElementGuid

-0.40

)));

-0.40

 rowIndex

-0.40

 Racine

-0.40

POSITIVE LOGITS

 stuff

2.31

stuff

2.05

 Stuff

2.02

 STUFF

1.98

Stuff

1.93

 stuffs

1.54

stuffs

1.06

 things

1.02

 crap

0.95

 stuffing

0.95

Activations Density 0.006%

references to vague or unspecified items

stuff and stuffing

No Known Activations