INDEX

Explanations

mathematical terms and symbols related to functions and sets

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

Mathematical notation or symbols

np_acts-logits-general · gemini-2.0-flash

in context of set membership

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

[++

-0.59

ùm

-0.52

 تضيفلها

-0.52

SerializedName

-0.52

 Waray

-0.51

 nakalista

-0.50

cator

-0.50

 LoggerFactory

-0.49

 acuity

-0.49

sph

-0.48

POSITIVE LOGITS

∈

1.03

∈

0.98

 thuộc

0.88

 belongs

0.79

 belong

0.79

 belonging

0.74

 appartenant

0.68

belong

0.67

perten

0.67

 pertence

0.66

Activations Density 0.841%

mathematical terms and symbols related to functions and sets

Mathematical notation or symbols

in context of set membership

No Comments

No Known Activations