INDEX

Explanations

references to pages in a document

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

"page" or "Page"

np_acts-logits-general · gemini-2.0-flash

page

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

degenerate

-0.58

ніципа

-0.53

ness

-0.53

-0.52

 ISNI

-0.51

 œil

-0.51

tagHelperRunner

-0.50

lowercase

-0.50

dagen

-0.50

webElementGuid

-0.49

POSITIVE LOGITS

antry

0.98

 turner

0.66

ants

0.64

views

0.60

break

0.56

ant

0.56

boy

0.54

ャ

0.54

ANT

0.53

vamp

0.53

Activations Density 0.056%

references to pages in a document

"page" or "Page"

page

No Comments

No Known Activations

references to pages in a document

"page" or "Page"

page

No Comments

No Known Activations