INDEX

Explanations

references to specific experiments or studies in the context of medical or scientific research

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

 AssemblyVersion

-0.85

IntoConstraints

-0.76

writeFieldEnd

-0.76

findpost

-0.73

antMatchers

-0.73

 gynnwys

-0.72

soort

-0.72

 <>",

-0.72

клопе

-0.71

AsUp

-0.71

POSITIVE LOGITS

auce

0.49

merking

0.45

isome

0.45

deus

0.44

Spes

0.43

 Général

0.43

ẓ

0.43

noopener

0.42

 médicale

0.42

 désol

0.42

Activations Density 0.266%

references to specific experiments or studies in the context of medical or scientific research

No Comments

No Known Activations