INDEX

Explanations

terms related to medical conditions and their identification methodologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Билгалдахарш

-0.53

الحياه

-0.53

 INTERESAR

-0.49

medy

-0.48

Kilder

-0.48

 jelen

-0.47

ómico

-0.47

 rire

-0.46

 plac

-0.46

 Dense

-0.45

POSITIVE LOGITS

 scopes

0.87

0.78

 scope

0.77

featureID

0.74

cope

0.74

AddTagHelper

0.73

Orth

0.71

PreferredItem

0.70

SourceChecksum

0.68

 Scope

0.68

Activations Density 2.684%

terms related to medical conditions and their identification methodologies

No Comments

No Known Activations