INDEX

Explanations

terms related to medical conditions and their classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Kies

-1.04

 Kell

-0.99

KDE

-0.95

 Kessel

-0.94

KP

-0.93

HasForeignKey

-0.93

 KeyError

-0.93

LEncoder

-0.92

kwds

-0.91

krb

-0.91

POSITIVE LOGITS

DOCT

0.55

Fle

0.55

 المق

0.54

 ilman

0.54

 Fleisch

0.54

 مرجع

0.53

 Imag

0.52

 مشين

0.52

tipation

0.51

 präsentiert

0.51

Activations Density 1.557%

terms related to medical conditions and their classifications

No Comments

No Known Activations