INDEX

Explanations

specific names and terms related to pharmaceutical 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 @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

Mej

-0.77

toggler

-0.75

 Stiles

-0.73

bouncycastle

-0.73

 Kull

-0.71

 pitching

-0.71

shadowColor

-0.71

avelin

-0.71

iverr

-0.70

 Balt

-0.69

POSITIVE LOGITS

peutic

0.83

ecore

0.74

rivial

0.72

 lenker

0.70

StructEnd

0.70

 Schal

0.69

estinal

0.68

 dụ

0.68

 Cheval

0.68

 AspNetCore

0.67

Activations Density 1.300%

specific names and terms related to pharmaceutical and medical contexts

No Comments

No Known Activations