INDEX

Explanations

references to individuals, specifically names or titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 nahilalakip

-1.04

AddTagHelper

-0.88

لينكات

-0.78

 CanadaChoose

-0.76

 AssemblyCulture

-0.72

قایناقلار

-0.70

Enllaces

-0.68

TagMode

-0.68

icolon

-0.68

unhofer

-0.68

POSITIVE LOGITS

 iprot

0.54

 faute

0.49

BindView

0.44

None

0.44

tex

0.43

bì

0.42

nytimes

0.40

が進

0.39

 resim

0.39

NYT

0.38

Activations Density 0.106%

references to individuals, specifically names or titles

No Comments

No Known Activations