INDEX

Explanations

programming terms and constructs, particularly those related to API requests and software components

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

mathematical and code symbols

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

'))

-0.37

'))

-0.36

']]

-0.35

InputBorder

-0.34

if

-0.34

Hob

-0.33

RefNanny

-0.33

RegistryLite

-0.33

fa

-0.32

fass

-0.32

POSITIVE LOGITS

 purpoſe

0.70

0.68

 GenerationType

0.64

 myſelf

0.63

 ſte

0.63

 ſtand

0.60

 ſta

0.59

 pleaſure

0.58

 preſent

0.57

 Reſ

0.56

Activations Density 0.010%

programming terms and constructs, particularly those related to API requests and software components

mathematical and code symbols

No Comments

No Known Activations