INDEX

Explanations

words related to health conditions and medical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 InputDecoration

-0.59

 rechange

-0.51

>//

-0.50

acă

-0.49

 fourrure

-0.48

 Meksiku

-0.48

onAttach

-0.47

Merchant

-0.46

колко

-0.44

 MALE

-0.43

POSITIVE LOGITS

RenderAtEndOf

0.85

ImageContext

0.63

ngdoc

0.61

EndInit

0.59

offsetof

0.59

RepeatedField

0.58

findpost

0.57

 Belong

0.54

 Puis

0.54

MigrationBuilder

0.53

Activations Density 0.680%

words related to health conditions and medical contexts

No Comments

No Known Activations