INDEX

Explanations

technical terms related to data structures and responses

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

json, Module, Response, Constant, Modifiers

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

RenderAtEndOf

-0.75

 himo

-0.66

⤹

-0.60

 Infórmanos

-0.58

évaluateur

-0.56

localctx

-0.56

 мәкал

-0.55

Sucesor

-0.55

abestanden

-0.54

QSize

-0.54

POSITIVE LOGITS

URLException

0.56

twimg

0.47

 gantung

0.32

HasForeignKey

0.31

 brevis

0.30

 spheres

0.29

出版年

0.29

uoš

0.28

المكان

0.28

 Fernsehen

0.27

Activations Density 0.010%

technical terms related to data structures and responses

json, Module, Response, Constant, Modifiers

No Comments

No Known Activations