INDEX

Explanations

terms related to medical research and chemistry

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 Nunn

-0.85

Gabi

-0.76

 Ellis

-0.75

 droplets

-0.75

ostro

-0.72

 Herrera

-0.71

iong

-0.70

 Gabi

-0.69

OSIS

-0.69

 Torres

-0.69

POSITIVE LOGITS

ValueStyle

1.10

 stiefel

0.98

 كومونز

0.93

 carav

0.93

 Carleton

0.91

."</

0.90

 Theſe

0.89

enumii

0.88

 benef

0.88

fällig

0.87

Activations Density 1.634%

terms related to medical research and chemistry

No Comments

No Known Activations