INDEX

Explanations

references to symptoms

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

makedirs

-0.65

ttino

-0.63

 Heide

-0.61

Esti

-0.59

viertel

-0.59

GetKey

-0.57

zugehen

-0.53

schra

-0.53

 localVar

-0.53

 Sald

-0.53

POSITIVE LOGITS

 symptoms

1.48

Symptoms

1.26

symptoms

1.23

 symptom

1.15

 Symptom

1.15

 Symptoms

1.11

 CreateTagHelper

0.99

Symptom

0.98

 symptômes

0.91

 síntomas

0.88

Activations Density 0.023%

references to symptoms

No Comments

No Known Activations