INDEX

Explanations

terms related to measurements or quantities in academic contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

set

-0.46

ran

-0.45

 focus

-0.44

↵

-0.44

run

-0.40

手的

-0.40

</strong>

-0.40

 decision

-0.40

 strictly

-0.39

 capital

-0.39

POSITIVE LOGITS

 estekak

0.76

 nakalista

0.73

лтемелер

0.72

EDEFAULT

0.70

sizeCache

0.70

Personensuche

0.69

 препратки

0.69

 lenker

0.68

AddHtmlAttribute

0.67

IsContent

0.67

Activations Density 0.001%

terms related to measurements or quantities in academic contexts

No Comments

No Known Activations