INDEX

Explanations

phrases indicating risk, adverse effects, and negative outcomes in clinical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

windowFixed

-0.47

taminophen

-0.45

_{*}

-0.45

thenReturn

-0.44

CppMethod

-0.44

CreateModel

-0.43

non

-0.43

ROIT

-0.42

GEBURTSDATUM

-0.41

 bodyParser

-0.41

POSITIVE LOGITS

0.80

 hoeft

0.71

ύτε

0.68

actylus

0.65

intenance

0.64

CloseOperation

0.61

Ārējās

0.61

redos

0.59

 arşivlendi

0.58

 /\.(

0.58

Activations Density 1.037%

phrases indicating risk, adverse effects, and negative outcomes in clinical contexts

No Comments

No Known Activations