INDEX

Explanations

specific names, titles, or entities referred to in the text

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

names and descriptors followed by punctuation

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

IndentedString

-0.60

ErrUnexpectedEOF

-0.57

RegistryLite

-0.56

Bakgrunnsstoff

-0.55

 HttpNotFound

-0.53

httphttps

-0.52

 Signalez

-0.52

MemoryWarning

-0.51

 GoogleFonts

-0.51

MLLoader

-0.50

POSITIVE LOGITS

 This

0.51

 Because

0.44

 Basically

0.41

Personendaten

0.41

 because

0.40

This

0.40

Because

0.40

 बि

0.39

 BrowserModule

0.38

It

0.37

Activations Density 0.172%

specific names, titles, or entities referred to in the text

names and descriptors followed by punctuation

No Comments

No Known Activations