INDEX

Explanations

references to specific proteins or molecular elements in scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

consulté

-0.69

igate

-0.66

Semitism

-0.62

anyahu

-0.62

kháu

-0.59

}?>

-0.59

]';

-0.59

poptosis

-0.58

makeText

-0.58

日閲覧

-0.57

POSITIVE LOGITS

Cap

0.85

Cap

0.84

Captor

0.84

CAP

0.79

Tē

0.77

 caps

0.73

 Caps

0.73

CAP

0.73

cap

0.72

Kap

0.68

Activations Density 0.096%

references to specific proteins or molecular elements in scientific contexts

No Comments

No Known Activations