INDEX

Explanations

elements from programming or code-related contexts

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

 متعلقه

-0.88

AddTagHelper

-0.83

StoreMessageInfo

-0.78

IsContent

-0.77

utilisons

-0.77

TagMode

-0.76

makeConstraints

-0.73

 AssemblyCulture

-0.69

IUrlHelper

-0.68

TableAdapter

-0.68

POSITIVE LOGITS

temon

0.40

quirrel

0.38

setLayoutManager

0.38

phorus

0.37

bed

0.36

 rush

0.35

 пун

0.35

ouro

0.35

ποίη

0.35

dbo

0.35

Activations Density 0.210%

elements from programming or code-related contexts

No Comments

No Known Activations