INDEX

Explanations

technical terms and components related to software configuration and programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

二是

-0.68

setLine

-0.57

Độ

-0.56

onAdd

-0.54

aarrggbb

-0.54

 vean

-0.53

worpen

-0.53

kranz

-0.53

czych

-0.52

 Serbs

-0.52

POSITIVE LOGITS

RectangleBorder

0.76

 eventdata

0.67

InvalidProtocol

0.66

 resourceCulture

0.64

StreetMap

0.64

 المعيارى

0.63

InputBorder

0.61

SerializedSize

0.60

 referrerpolicy

0.59

原始内容存档于

0.58

Activations Density 1.417%

technical terms and components related to software configuration and programming

No Comments

No Known Activations