INDEX

Explanations

key phrases and actions related to prompts, inquiries, and interactions

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

headings or introductions

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

 мәкал

-0.72

 snippetHide

-0.65

 Normdatei

-0.61

 tartalomajánló

-0.56

 nakalista

-0.53

 mijne

-0.53

новниш

-0.52

 RIPRODUZIONE

-0.52

IsContent

-0.51

ngrx

-0.50

POSITIVE LOGITS

0.52

ArgsConstructor

0.39

ässig

0.39

 Administr

0.36

 stade

0.35

 tunt

0.35

...

0.34

 interesar

0.34

Життєпис

0.34

 CURIAM

0.33

Activations Density 0.031%

key phrases and actions related to prompts, inquiries, and interactions

headings or introductions

No Comments

No Known Activations