INDEX

Explanations

code structure and function definitions in programming languages

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

variable names and code syntax

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

Kast

-0.45

aps

-0.43

CAS

-0.41

회

-0.41

cada

-0.41

sl

-0.39

 swing

-0.39

net

-0.38

mib

-0.38

eman

-0.38

POSITIVE LOGITS

 surla

0.71

writeFieldEnd

0.69

 ब्रेकडाउन

0.66

tagHelperRunner

0.63

ValueStyle

0.61

 disambiguazione

0.61

XmlAccessorType

0.56

帖最后由

0.55

 Signalez

0.53

webElementXpaths

0.53

Activations Density 0.019%

code structure and function definitions in programming languages

variable names and code syntax

No Comments

No Known Activations