INDEX

Explanations

terms related to smoking or tobacco consumption

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

躇

-0.89

EndProject

-0.85

 Klee

-0.80

 Heuer

-0.80

WebVitals

-0.77

Hozzáférés

-0.73

/*

-0.73

inthians

-0.73

์

-0.72

WebControls

-0.72

POSITIVE LOGITS

 smoke

1.67

 smoking

1.64

Smo

1.62

Smo

1.58

 smoker

1.56

 Smoking

1.55

 smokers

1.53

smoking

1.48

 smokes

1.46

smoke

1.45

Activations Density 0.188%

terms related to smoking or tobacco consumption

No Comments

No Known Activations