INDEX

Explanations

terms related to neurodegenerative diseases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

導

-0.57

氓

-0.56

Iso

-0.53

导

-0.52

import

-0.51

 чи

-0.50

Wir

-0.48

Wir

-0.48

useEffect

-0.48

 poca

-0.48

POSITIVE LOGITS

parsedMessage

0.84

standers

0.77

Lam

0.77

Lam

0.76

bleau

0.76

ViewFeatures

0.73

 BoxDecoration

0.72

ntö

0.72

 Monfieur

0.71

 Sharon

0.69

Activations Density 0.100%

terms related to neurodegenerative diseases

No Comments

No Known Activations