INDEX

Explanations

references to medical or health-related topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 Publication

-0.84

 publication

-0.76

twimg

-0.76

 publishing

-0.72

Publication

-0.71

 publisher

-0.71

 Publications

-0.71

 publish

-0.69

 出版

-0.68

 publishes

-0.67

POSITIVE LOGITS

 explanations

0.83

 explanation

0.83

 suggestion

0.80

 suggestions

0.79

 guesses

0.78

 discussion

0.76

 advice

0.76

 questions

0.74

 explained

0.74

 guessed

0.74

Activations Density 2.721%

references to medical or health-related topics

No Comments

No Known Activations