INDEX

Explanations

terms related to medical or scientific contexts, particularly references to information and evidence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 boneco

-0.42

 Fleisch

-0.41

 roupa

-0.40

 Menschheit

-0.40

 maquiagem

-0.39

 colectivos

-0.39

 colectivo

-0.39

 muñeco

-0.39

 Movimiento

-0.38

 oignon

-0.38

POSITIVE LOGITS

inf

0.81

inf

0.80

 cite

0.77

ref

0.72

Inf

0.71

 citing

0.70

 citations

0.69

цездатний

0.69

cit

0.69

bib

0.69

Activations Density 0.332%

terms related to medical or scientific contexts, particularly references to information and evidence

No Comments

No Known Activations