INDEX

Explanations

the character "Ke" followed by various suffixes or contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

SourceChecksum

-0.79

Portail

-0.75

LookAnd

-0.67

 للاسماء

-0.64

RectangleBorder

-0.60

}{@

-0.56

resor

-0.53

ImageContext

-0.52

unanje

-0.51

POSITIVE LOGITS

Ke

1.17

Ke

0.91

ke

0.84

ny

0.80

Workflow

0.76

stock

0.72

STOCK

0.68

Ny

0.67

 quanti

0.67

Quanti

0.65

Activations Density 0.041%

the character "Ke" followed by various suffixes or contexts

No Comments

No Known Activations

the character "Ke" followed by various suffixes or contexts

No Comments

No Known Activations