INDEX

Explanations

references to films and their qualities or attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 trône

-0.88

 löyty

-0.70

 affez

-0.69

 récon

-0.68

 kysy

-0.68

 vétérina

-0.67

ırlı

-0.66

 compréhen

-0.66

 étrang

-0.66

ANTAGE

-0.66

POSITIVE LOGITS

 film

2.17

 films

2.03

 FILM

1.95

 Film

1.94

film

1.86

Film

1.76

 Films

1.67

FILM

1.66

films

1.61

Films

1.54

Activations Density 0.042%

references to films and their qualities or attributes

No Comments

No Known Activations