INDEX

Explanations

terms related to smoking and tobacco use

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

WebVitals

-0.95

躇

-0.86

 الحره

-0.79

elesai

-0.72

 Compiler

-0.70

 EconPapers

-0.70

ElementException

-0.70

 hâte

-0.70

DetailComponent

-0.69

/*

-0.69

POSITIVE LOGITS

 smoke

2.66

 smoking

2.52

 Smoke

2.31

 Smoking

2.26

smoke

2.24

 smokes

2.20

smoking

2.16

Smoke

2.16

 smokers

2.14

 smoker

2.10

Activations Density 0.049%

terms related to smoking and tobacco use

No Comments

No Known Activations