INDEX

Explanations

references to governmental or organizational entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-mlp-65k

Configuration

google/gemma-scope-2b-pt-mlp/layer_0/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.0.hook_mlp_out

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

 InputDecoration

-0.76

ContentAsync

-0.68

 TestBed

-0.66

 समीक्षाएं

-0.65

contentLoaded

-0.63

GenerationType

-0.62

RunAsync

-0.58

tvguidetime

-0.57

Gost

-0.57

TagHelpers

-0.57

POSITIVE LOGITS

campal

0.61

PickerController

0.57

merce

0.56

 autorytatywna

0.56

nsics

0.54

ing

0.52

enegro

0.52

nsic

0.51

stris

0.51

ISPR

0.51

Activations Density 0.039%

references to governmental or organizational entities

No Comments

No Known Activations