INDEX

Explanations

structured data formats

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

Numbers or hexadecimal values

np_acts-logits-general · gemini-2.0-flash

numbers, codes, and identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 betweenstory

-1.09

ftagPool

-0.95

 CreateTagHelper

-0.85

findpost

-0.82

AndEndTag

-0.80

protoimpl

-0.79

 NSCoder

-0.77

GEBURTSDATUM

-0.76

MigrationBuilder

-0.73

 ivelany

-0.71

POSITIVE LOGITS

ARIS

0.57

paravant

0.56

ination

0.55

key

0.55

 follow

0.54

det

0.54

ierno

0.54

EMAS

0.53

ENIE

0.53

cheur

0.53

Activations Density 0.376%

structured data formats

Numbers or hexadecimal values

numbers, codes, and identifiers

No Comments

No Known Activations