INDEX

Explanations

references to specific individuals and their actions or contributions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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

 referenties

-0.60

ématique

-0.55

arum

-0.54

 MonoBehaviour

-0.53

 listening

-0.50

SharedCtor

-0.49

 OMITBAD

-0.48

buntu

-0.48

 wondering

-0.48

ucca

-0.48

POSITIVE LOGITS

>`;

0.66

 OBITUARY

0.66

 AttributeSet

0.62

WriteTagHelper

0.62

devamını

0.58

"]));

0.57

}}$\\

0.57

 termed

0.53

addContainerGap

0.52

 οποία

0.52

Activations Density 0.236%

references to specific individuals and their actions or contributions

No Comments

No Known Activations