INDEX

Explanations

abbreviations or codes used in technical specifications

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

IPPROTO_* and DLT_* constants

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

ſelf

-0.62

ſelves

-0.49

ſure

-0.46

addCriterion

-0.44

 Houſe

-0.42

hyo

-0.40

անգ

-0.40

iveau

-0.39

ſures

-0.38

Repe

-0.38

POSITIVE LOGITS

########.

0.53

 nakalista

0.49

rungsseite

0.47

 nahilalakip

0.47

RTEE

0.46

 CURLOPT

0.44

gunos

0.44

OrNil

0.39

urlopen

0.39

cticut

0.39

Activations Density 0.018%

abbreviations or codes used in technical specifications

IPPROTO_* and DLT_* constants

No Comments

No Known Activations