INDEX

Explanations

references to extraction options and json object manipulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

PYX

-0.52

aarrggbb

-0.49

loem

-0.48

 AdapterView

-0.47

 contemporaries

-0.47

 Jody

-0.47

avits

-0.46

 setting

-0.46

KEYCODE

-0.46

 Shand

-0.45

POSITIVE LOGITS

 &___

0.73

dataclass

0.69

RetentionPolicy

0.64

exitRule

0.61

 InputDecoration

0.59

LEncoder

0.57

MessageOf

0.56

 مرئيه

0.55

руппа

0.53

ArgsConstructor

0.53

Activations Density 0.344%

references to extraction options and json object manipulations

No Comments

No Known Activations