INDEX

Explanations

references to operatic roles and works

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

 Poehler

-0.57

مصادر

-0.52

脚注の使い方

-0.52

 Beecher

-0.52

یکن

-0.51

twimg

-0.50

:+:

-0.50

AndEndTag

-0.49

ArgsConstructor

-0.49

kloped

-0.48

POSITIVE LOGITS

 opera

1.14

opera

0.97

 operas

0.92

 Opera

0.92

Opera

0.88

 Oper

0.85

 oper

0.84

 OPER

0.83

 operar

0.77

Opéra

0.72

Activations Density 0.072%

references to operatic roles and works

No Comments

No Known Activations