INDEX

Explanations

HTML tags and attributes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

webElementXpaths

-1.03

UserScript

-0.92

 betweenstory

-0.91

 Мексичка

-0.87

Rüyada

-0.86

 Wikimedijinoj

-0.83

stateProvider

-0.81

kháu

-0.81

mybatisplus

-0.79

 Meksiku

-0.78

POSITIVE LOGITS

<eos>

0.72

[toxicity=0]

0.61

 even

0.61

0.59

 rowspan

0.56

 still

0.56

<b>

0.54

 mathvariant

0.53

><

0.52

<tr>

0.51

Activations Density 0.250%

HTML tags and attributes

No Comments

No Known Activations