INDEX

Explanations

medical situations involving injuries or health-related incidents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

rinol

-0.51

immt

-0.50

ReusableCell

-0.50

}{*}{}

-0.48

gjenge

-0.47

Diweddarwch

-0.46

 dictadura

-0.44

いれば

-0.43

ctibles

-0.43

newswire

-0.43

POSITIVE LOGITS

 accidentally

1.07

 accidental

0.84

 inadvertently

0.77

 caught

0.74

 accident

0.73

 Accidental

0.71

accident

0.70

 broke

0.70

 unintentionally

0.69

 mishap

0.67

Activations Density 0.393%

medical situations involving injuries or health-related incidents

No Comments

No Known Activations