INDEX

Explanations

variations of the word "super" in different forms and contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

alga

-0.70

 kaynağından

-0.68

 inté

-0.68

 Audiodateien

-0.68

 Neale

-0.67

tableFuture

-0.67

 orde

-0.65

⃗

-0.64

Erl

-0.64

 fatores

-0.64

POSITIVE LOGITS

SUP

1.05

 supervisors

0.99

SUP

0.98

 Suri

0.96

 Supers

0.94

Sup

0.91

Supers

0.91

Sup

0.91

 supervisor

0.90

 Supper

0.89

Activations Density 0.144%

variations of the word "super" in different forms and contexts

No Comments

No Known Activations