INDEX

Explanations

technical terms and identifiers related to programming and web development

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

elemField

-0.86

 téléph

-0.76

NewUrlParser

-0.73

 odkazy

-0.68

StreetMap

-0.68

verwijspagina

-0.66

 découver

-0.66

RepeatedField

-0.66

енча

-0.65

↹

-0.64

POSITIVE LOGITS

($__

0.75

={`/

0.57

 sandero

0.55

CGContext

0.54

_('

0.51

 info

0.51

 сожалению

0.49

 Karma

0.49

 infor

0.48

aire

0.47

Activations Density 1.144%

technical terms and identifiers related to programming and web development

No Comments

No Known Activations