INDEX

Explanations

references to dietary supplements and related terms

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

 Wayback

-0.73

compli

-0.67

RenderAtEndOf

-0.62

Odon

-0.60

 erec

-0.58

RegressionTest

-0.55

Compli

-0.54

нъ

-0.53

ImageContext

-0.53

 Rango

-0.53

POSITIVE LOGITS

 supplement

1.46

 Supplement

1.30

supplement

1.29

 supplements

1.17

Supplement

1.14

 supplementing

1.07

 partly

1.01

 SUPPLEMENT

1.00

 supplementation

1.00

 supplemented

1.00

Activations Density 0.070%

references to dietary supplements and related terms

No Comments

No Known Activations