INDEX

Explanations

mentions of the word "famous" and associated descriptors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 InputDecoration

-0.69

illères

-0.65

 Kigali

-0.63

 Enugu

-0.62

quirrels

-0.62

qin

-0.61

ContentAlignment

-0.60

 Polis

-0.58

Alberta

-0.58

 spie

-0.58

POSITIVE LOGITS

 Famous

1.53

 famous

1.52

famous

1.49

Famous

1.40

 famosa

1.15

 famosos

1.15

 famoso

1.14

 fame

1.09

 famed

1.08

 infamous

1.07

Activations Density 0.071%

mentions of the word "famous" and associated descriptors

No Comments

No Known Activations