INDEX

Explanations

percentages and their associated ratios or comparisons

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

percentages followed by context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

 except

-0.27

 recently

-0.26

sp

-0.26

except

-0.26

 Recent

-0.26

 names

-0.25

便利です

-0.25

 ingenting

-0.24

 WATCH

-0.24

WATCH

-0.24

POSITIVE LOGITS

GEBURTSDATUM

0.81

SharedDtor

0.80

 '\\;'

0.74

migrationBuilder

0.73

лтамалар

0.71

FunctionFlags

0.70

RUnlock

0.69

bootstrapcdn

0.69

EDEFAULT

0.68

endphp

0.65

Activations Density 0.078%

percentages and their associated ratios or comparisons

percentages followed by context

No Comments

No Known Activations