INDEX

Explanations

terms related to nobility or titles of address

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

verwijspagina

-0.79

oredCriteria

-0.76

LookAnd

-0.76

 tartalomajánló

-0.75

 nahilalakip

-0.72

Erreferentziak

-0.72

 للاسماء

-0.71

createCanvas

-0.69

__':

-0.69

protoimpl

-0.67

POSITIVE LOGITS

 Appreciation

0.68

 appreciation

0.67

 appreciate

0.64

之

0.61

 cares

0.60

 appreci

0.59

sco

0.53

 cared

0.53

 care

0.52

 appreciating

0.51

Activations Density 0.178%

terms related to nobility or titles of address

No Comments

No Known Activations