INDEX

Explanations

terms related to programming, especially in the context of defining functions and parameters

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

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

WebpackPlugin

-0.67

 doInBackground

-0.63

extendable

-0.61

הערות

-0.56

minal

-0.54

 appellant

-0.54

 Monfieur

-0.53

gantes

-0.53

 članak

-0.53

tonode

-0.51

POSITIVE LOGITS

ustice

0.74

ความ

0.72

 strength

0.70

urity

0.69

 violence

0.67

ignty

0.67

vity

0.66

 fertility

0.65

 energy

0.65

 maturity

0.65

Activations Density 0.339%

terms related to programming, especially in the context of defining functions and parameters

No Comments

No Known Activations