INDEX

Explanations

numeric values and counts

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

Numbers or code snippets

np_acts-logits-general · gemini-2.0-flash

numbers followed by punctuation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

-0.57

-0.55

“

-0.55

ern

-0.54

the

-0.54

’

-0.54

of

-0.54

-0.53

 present

-0.53

POSITIVE LOGITS

IntoConstraints

1.04

AndEndTag

0.98

ConstraintMaker

0.98

 NSCoder

0.87

MigrationBuilder

0.82

RectangleBorder

0.78

 myſelf

0.77

 CURIAM

0.76

 quæ

0.76

IsMutable

0.76

Activations Density 0.747%

numeric values and counts

Numbers or code snippets

numbers followed by punctuation

No Comments

No Known Activations