INDEX

Explanations

the beginning or end of structured documents or sections

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

Code or special characters

np_acts-logits-general · gemini-2.0-flash

code, math, and citations

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

didSet

-0.56

 number

-0.52

دانشنامهٔ

-0.48

 CGFloat

-0.48

 personally

-0.47

mato

-0.47

Her

-0.45

 volume

-0.45

 sien

-0.44

CIC

-0.44

POSITIVE LOGITS

abestanden

0.80

ContentAsync

0.70

 Roskov

0.68

abinieri

0.66

principalTable

0.66

ReferenceEquals

0.65

 препратки

0.64

 Signalez

0.62

 ***!

0.61

 surla

0.60

Activations Density 0.127%

the beginning or end of structured documents or sections

Code or special characters

code, math, and citations

No Comments

No Known Activations