INDEX

Explanations

code-like structures and tags typically associated with programming and markup languages

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

HomeAsUpEnabled

-0.74

XmlAccessorType

-0.68

存于互联网档案馆

-0.68

SequentialGroup

-0.67

 }}"></

-0.66

 дис

-0.65

umumkan

-0.64

homonymie

-0.64

SBATCH

-0.63

Hozzáférés

-0.62

POSITIVE LOGITS

 betweenstory

0.92

aarrggbb

0.69

PreferredItem

0.69

RegressionTest

0.66

Hentet

0.59

évaluateur

0.55

 untitled

0.54

awtextra

0.50

windowFixed

0.50

 Reverso

0.48

Activations Density 0.033%

code-like structures and tags typically associated with programming and markup languages

No Comments

No Known Activations