INDEX

Explanations

proper nouns and specific references in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

انيف

-0.60

spesies

-0.56

beta

-0.53

Beta

-0.53

 LoggerFactory

-0.52

IRUS

-0.51

β

-0.51

verwijspagina

-0.49

 Frankel

-0.49

 ErrIntOverflow

-0.48

POSITIVE LOGITS

 Roast

0.84

 Roberta

0.81

ROB

0.80

 Rovers

0.77

ro

0.76

 Robe

0.76

ro

0.76

 Rosalie

0.75

Ro

0.73

RO

0.73

Activations Density 3.176%

proper nouns and specific references in various contexts

No Comments

No Known Activations