INDEX

Explanations

proper nouns related to companies, characters, and products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 Japan

-0.75

 оригіналу

-0.74

Japan

-0.68

 Tokyo

-0.66

 japan

-0.65

fjspx

-0.65

 Japanese

-0.64

ercises

-0.63

(!__

-0.63

JAPAN

-0.62

POSITIVE LOGITS

AndEndTag

0.59

elemField

0.50

 gyak

0.49

WebVitals

0.48

 createSlice

0.48

no

0.46

 snippetHide

0.46

DOCTYPE

0.45

baiki

0.44

 Dense

0.43

Activations Density 0.261%

proper nouns related to companies, characters, and products

No Comments

No Known Activations