INDEX

Explanations

mentions of first-time occurrences and significant debut events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ķ

-0.43

 abuse

-0.38

 సౌకర్య

-0.37

PyExc

-0.37

 pate

-0.36

Rover

-0.36

ियाँ

-0.36

 câte

-0.36

 cream

-0.35

瑞士

-0.35

POSITIVE LOGITS

脚注の使い方

0.93

 nahilalakip

0.91

parsedMessage

0.86

AddHtmlAttribute

0.84

:✨

0.84

InputBorder

0.83

tableFuture

0.82

CloseOperation

0.81

 ever

0.81

viewDidLoad

0.79

Activations Density 0.186%

mentions of first-time occurrences and significant debut events

No Comments

No Known Activations