INDEX

Explanations

scientific notations and expressions involving variables and mathematical symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 ProtoMessage

-0.76

RegressionTest

-0.72

InjectAttribute

-0.67

 typelib

-0.66

Tikang

-0.65

sidemargin

-0.63

 jsPsych

-0.63

 >=",

-0.63

 ***!

-0.63

SourceChecksum

-0.61

POSITIVE LOGITS

 others

0.68

 ones

0.62

 Others

0.61

 voire

0.60

 near

0.57

others

0.57

Others

0.56

뀜

0.55

 thereof

0.55

 gynhyrchwyd

0.54

Activations Density 1.316%

scientific notations and expressions involving variables and mathematical symbols

No Comments

No Known Activations