INDEX

Explanations

specific terminology related to computing or programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

stateMutability

-0.71

 FILED

-0.57

balleur

-0.56

UnitTesting

-0.55

RenderAtEndOf

-0.55

/**

-0.54

 HasFactory

-0.54

-------------</

-0.52

ereien

-0.52

oader

-0.52

POSITIVE LOGITS

 typelib

0.59

rhosis

0.55

claimers

0.54

 reading

0.52

metingen

0.52

<bos>

0.51

ebbe

0.51

 beginnetje

0.50

הערות

0.49

 readers

0.48

Activations Density 0.625%

specific terminology related to computing or programming

No Comments

No Known Activations