INDEX

Explanations

references to patents and patent applications

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

patent references

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

LookAnd

-0.53

IUrlHelper

-0.51

Jeografia

-0.43

UserScript

-0.42

 poved

-0.42

-0.39

锈钢

-0.39

发表于

-0.38

 Hoog

-0.38

POSITIVE LOGITS

balleur

0.47

ocities

0.44

öglichkeiten

0.40

 BorderSide

0.40

 Unmarshal

0.39

 BoxFit

0.38

 snippetHide

0.38

 Chrysler

0.38

 forestry

0.37

 fabricants

0.37

Activations Density 0.012%

references to patents and patent applications

patent references

No Comments

No Known Activations