INDEX

Explanations

references to years and time periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

ŝ

-0.60

tiliz

-0.56

послед

-0.55

vč

-0.53

Mong

-0.53

 Astronomical

-0.52

pable

-0.51

 последний

-0.51

Rowan

-0.51

tachment

-0.50

POSITIVE LOGITS

+#+

1.11

decade

1.01

 Monfieur

0.90

 OFDb

0.90

 Мексичка

0.88

decade

0.87

onAttach

0.86

ANDUM

0.85

StandardCharsets

0.85

Decade

0.83

Activations Density 0.084%

references to years and time periods

No Comments

No Known Activations