INDEX

Explanations

mentions of significant events or milestones, particularly related to personal or narrative outcomes

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

 ModelRenderer

-0.56

SourceChecksum

-0.53

脚注の使い方

-0.52

HostException

-0.51

Tikang

-0.50

ClientRect

-0.49

aarrggbb

-0.48

 ProtoMessage

-0.47

EDEFAULT

-0.46

Aholisi

-0.46

POSITIVE LOGITS

Décès

0.46

⏪

0.36

啱

0.35

 window

0.35

 glazing

0.35

 Bluffs

0.35

 Mako

0.34

Deps

0.34

 hiding

0.34

蒸

0.34

Activations Density 0.273%

mentions of significant events or milestones, particularly related to personal or narrative outcomes

No Comments

No Known Activations