INDEX

Explanations

relationships and connections between entities or concepts

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

code comments and technical english/french phrases

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

Tikang

-0.41

testens

-0.38

 dieux

-0.38

 tráiler

-0.35

 μην

-0.34

MarshalTo

-0.34

ulents

-0.33

Collaboration

-0.33

 mengajar

-0.33

ROLLER

-0.33

POSITIVE LOGITS

ThroughAttribute

0.70

__":

0.59

UserScript

0.54

 NSCoder

0.54

Chham

0.52

quelize

0.52

EndGlobalSection

0.49

__(/*!

0.48

хьтан

0.48

AddHtmlAttribute

0.47

Activations Density 0.036%

relationships and connections between entities or concepts

code comments and technical english/french phrases

No Comments

No Known Activations