INDEX

Explanations

terms related to post-operative 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 @ 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

 المعيارى

-0.56

bbene

-0.52

 esfor

-0.52

Kilder

-0.52

 purpoſe

-0.51

]-->

-0.50

 ſta

-0.50

YTICAL

-0.49

 segura

-0.49

ształ

-0.48

POSITIVE LOGITS

 post

0.91

 Post

0.83

 POST

0.77

post

0.74

 getPost

0.70

Post

0.70

ポスト

0.60

 समीक्षक

0.57

Portale

0.56

 ポスト

0.55

Activations Density 0.201%

terms related to post-operative medical contexts

No Comments

No Known Activations