INDEX

Explanations

terminology related to academic research and analysis methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.58

("

-0.54

—

-0.52

('

-0.52

 (“

-0.46

 (‘

-0.45

—

-0.45

 vanguardia

-0.43

(`

-0.42

 znamen

-0.42

POSITIVE LOGITS

 itſelf

1.16

 itself

1.01

 myſelf

1.00

 himſelf

0.87

itself

0.85

ⓧ

0.84

 purpoſe

0.81

KURZBESCHREIBUNG

0.80

 poffe

0.79

 Majefty

0.79

Activations Density 0.525%

terminology related to academic research and analysis methods

No Comments

No Known Activations