INDEX

Explanations

technical terms and phrases related to parsing and media types

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

tanooga

-0.69



-0.68

uminense

-0.65

 estekak

-0.63

derabad

-0.62

/*

-0.61

SharedCtor

-0.60

ьаж

-0.59

 toga

-0.59

Rese

-0.58

POSITIVE LOGITS

 literacy

0.67

fer

0.66

 grip

0.66

ymce

0.64

ido

0.64

Mol

0.62

Fer

0.61

 grips

0.60

 pronon

0.59

fer

0.58

Activations Density 1.911%

technical terms and phrases related to parsing and media types

No Comments

No Known Activations