INDEX

Explanations

phrases related to political critique and personal responsibility

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

between specific language and unrelated terms

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

stle

-0.37

 ramai

-0.36

providedIn

-0.36

pina

-0.35

 heart

-0.35

ostí

-0.35

 prestige

-0.35

heart

-0.34

 proced

-0.34

 Heart

-0.34

POSITIVE LOGITS

 betweenstory

0.55

GeneratedMessage

0.50

oredCriteria

0.48

stateProvider

0.46

VIAF

0.45

 actually

0.45

CodedInputStream

0.45

:✨

0.44

竟然

0.43

 Ressources

0.42

Activations Density 0.125%

phrases related to political critique and personal responsibility

between specific language and unrelated terms

No Comments

No Known Activations