INDEX

Explanations

phrases that indicate storytelling or narrative elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

issor

-0.47

tow

-0.43

Baj

-0.38

ProgressHUD

-0.37

bej

-0.37

 testified

-0.36

Persist

-0.36

 ſaid

-0.36

Gord

-0.36

 kulture

-0.36

POSITIVE LOGITS

AccessorTable

0.64

 мәкал

0.60

XmlAccessorType

0.55

UrlResolution

0.52

principalTable

0.52

 HasFactory

0.50

ScopeManager

0.50

 beginnetje

0.49

ArgumentParser

0.49

IGraphics

0.46

Activations Density 0.552%

phrases that indicate storytelling or narrative elements

No Comments

No Known Activations