INDEX

Explanations

occurrences of significant political events or scandals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 myſelf

-0.83

 purpoſe

-0.79

 Shakspeare

-0.78

 itſelf

-0.74

 houſe

-0.72

 Monfieur

-0.72

 Houſe

-0.71

 Jefus

-0.70

 poffible

-0.69

 Majefty

-0.68

POSITIVE LOGITS

#+#

0.72

 desaparecido

0.65

########.

0.64

 reservado

0.61

 Kemp

0.59

 Persson

0.55

Marianne

0.55

gezogen

0.54

 Bort

0.54

 assuré

0.53

Activations Density 1.077%

occurrences of significant political events or scandals

No Comments

No Known Activations