INDEX

Explanations

connections to memories and personal experiences associated with objects and periods in life

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

associated with memories

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

Autoritní

-0.57

 مشين

-0.52

ustice

-0.50

ystick

-0.49

JsonPropertyName

-0.49

 referenties

-0.48

DataAnnotations

-0.47

MigrationBuilder

-0.46

 pyram

-0.45

 Infórmanos

-0.45

POSITIVE LOGITS

 memories

0.71

 memory

0.58

 associations

0.57

 herinner

0.56

 recuerdos

0.56

Memories

0.55

 estekak

0.53

 воспомина

0.52

 association

0.52

memories

0.52

Activations Density 0.021%

connections to memories and personal experiences associated with objects and periods in life

associated with memories

No Comments

No Known Activations