INDEX

Explanations

elements related to medical diagnoses and physical conditions

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

MessageTagHelper

-1.08

rungsseite

-1.05

 Hake

-0.83

ReusableCell

-0.76

 Bateman

-0.76

 TestBed

-0.72

Pulp

-0.72

 Chichester

-0.71

kum

-0.70

FormTagHelper

-0.70

POSITIVE LOGITS

 necks

0.86

 neck

0.76

 Tennessee

0.70

 pescoço

0.69

 Neck

0.68

 swans

0.67

ibouti

0.66

Neck

0.64

Tennessee

0.63

 Jovan

0.61

Activations Density 0.737%

elements related to medical diagnoses and physical conditions

No Comments

No Known Activations