INDEX

Explanations

technical terms and identifiers related to programming and computer science

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

hyrchwyd

-0.88

 חיצוניים

-0.78

LookAnd

-0.77

ThroughAttribute

-0.76

 otomatig

-0.73

saraba

-0.71

########.

-0.70

SharedCtor

-0.69

unknownFields

-0.66

AccessorTable

-0.65

POSITIVE LOGITS

orianCalendar

0.64

 ſhe

0.59

 myſelf

0.57

 Nedir

0.55

 himſelf

0.52

 itſelf

0.52

 themſelves

0.50

 oublié

0.50

 Anglais

0.50

 Giugno

0.49

Activations Density 1.069%

technical terms and identifiers related to programming and computer science

No Comments

No Known Activations