INDEX

Explanations

specific terms related to chess, legal terminology, medical contexts, and manufacturing processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

 surla

-0.91

 GenerationType

-0.84

ulemon

-0.83

 Roskov

-0.77

WebElementEntity

-0.77

parsedMessage

-0.77

RenderAtEndOf

-0.77

 beſte

-0.77

 ddelwed

-0.74

 snippetHide

-0.74

POSITIVE LOGITS

 traditional

0.42

 clássico

0.41

 classic

0.40

old

0.39

 tradicional

0.38

 historical

0.36

 classique

0.36

 traditionnel

0.36

 classical

0.36

kind

0.35

Activations Density 2.173%

specific terms related to chess, legal terminology, medical contexts, and manufacturing processes

No Comments

No Known Activations