INDEX

Explanations

references to clinical contexts and practices

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 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

antMatchers

-0.67

enumi

-0.61

Portály

-0.61

 honor

-0.59

 flavon

-0.58

ObjectContext

-0.56

DOCT

-0.56

 HONOR

-0.54

͡

-0.53

RetentionPolicy

-0.52

POSITIVE LOGITS

 <=",

0.84

ConstraintMaker

0.82

 autorytatywna

0.80

contentLoaded

0.77

 &___

0.72

__':

0.72

Clinical

0.69

PreferredItem

0.66

['$

0.65

fjspx

0.65

Activations Density 0.072%

references to clinical contexts and practices

No Comments

No Known Activations