INDEX

Explanations

configuration settings and parameters, especially in code and data structures

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

errHandler

-0.54

 Réponses

-0.47

AndEndTag

-0.46

ole

-0.46

去的

-0.42

 volna

-0.41

zional

-0.41

FailureListener

-0.41

 lưng

-0.40

phrine

-0.40

POSITIVE LOGITS

.*")]

0.76

 myſelf

0.73

 Majefty

0.73

 فريبيس

0.70

ſelves

0.70

ſelf

0.69

 becauſe

0.66

ГЛА

0.66

 Shakspeare

0.66

 Anſ

0.66

Activations Density 0.243%

configuration settings and parameters, especially in code and data structures

No Comments

No Known Activations