INDEX

Explanations

quantifiable measures or metrics, particularly those implied by numerical or statistical information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

httphttps

-0.64

uxxxx

-0.63

StoryboardSegue

-0.58

intios

-0.58

 iconTwitter

-0.57

󠁢

-0.57

 Walkover

-0.56

⟬

-0.55

UMENTS

-0.55

webElementXpaths

-0.53

POSITIVE LOGITS

flashdata

0.41

[toxicity=0]

0.34

<h6>

0.32

 situ

0.30

例文帳に追加

0.30

 ")");

0.28

("-");

0.28

Nah

0.28

叶修

0.28

textAppearance

0.27

Activations Density 0.515%

quantifiable measures or metrics, particularly those implied by numerical or statistical information

No Comments

No Known Activations