INDEX

Explanations

programming terms and constructs related to data handling and formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

XMLSchema

-0.89

featureID

-0.78

Архівовано

-0.74

LookAnd

-0.73

 Vikipedi

-0.71

InSection

-0.67

InstrumentedTest

-0.66

-0.65

 kaarangay

-0.65

ByVersion

-0.64

POSITIVE LOGITS

0.57

ſo

0.55

myArray

0.53

 jsonObj

0.53

 "'");

0.52

uſ

0.50

\""

0.50

pencer

0.50

ﬀ

0.50

Activations Density 0.208%

programming terms and constructs related to data handling and formatting

No Comments

No Known Activations