INDEX

Explanations

references to people

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

 livré

-0.64

 fourni

-0.59

 něm

-0.57

LogFactory

-0.57

Personendaten

-0.56

 tekem

-0.55

pośred

-0.55

 řízení

-0.54

ală

-0.54

 použití

-0.53

POSITIVE LOGITS

 people

0.94

people

0.81

People

0.80

 People

0.77

ppl

0.76

出版年

0.74

 things

0.72

 PEOPLE

0.68

osoever

0.67

PEOPLE

0.66

Activations Density 0.201%

references to people

No Comments

No Known Activations