INDEX

Explanations

patterns and structures in data, possibly related to programming or computation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 protoimpl

-0.66

TypedDataSet

-0.61

 مشين

-0.57

Jeografia

-0.56

حياته

-0.55

Tikang

-0.54

 <<<<<<<<<<<<<<

-0.54

 nakalista

-0.53

TagMode

-0.53

kozások

-0.52

POSITIVE LOGITS

valget

0.53

unload

0.48

tanleria

0.47

SupportActionBar

0.46

VOS

0.45

例文帳に追加

0.45

Portail

0.44

 edelstahl

0.44

desenho

0.44

ering

0.43

Activations Density 0.085%

patterns and structures in data, possibly related to programming or computation

No Comments

No Known Activations