INDEX

Explanations

the word "spec" and its variations related to specificity and specifications

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

The token "spec"

np_acts-logits-general · gemini-2.0-flash

spec, specular, specificity, specimens, speculates

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

ỏa

-0.49

nean

-0.48

webp

-0.47

AutoField

-0.47

fileupload

-0.46

┫

-0.46

 chargeable

-0.46

 ditemp

-0.46

 Qualified

-0.45

 وصلة

-0.45

POSITIVE LOGITS

 AssemblyCulture

0.85

 Spec

0.75

 spec

0.73

trums

0.66

 SPEC

0.65

جغرافيا

0.60

timeScale

0.59

QMetaType

0.58

Spec

0.57

styleType

0.57

Activations Density 0.274%

the word "spec" and its variations related to specificity and specifications

The token "spec"

spec, specular, specificity, specimens, speculates

No Comments

No Known Activations