INDEX

Explanations

sequences of alphanumeric characters representing data structures or commands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

帖最后由

-0.84

Odkazy

-0.63

IUrlHelper

-0.52

WarningLevel

-0.51

tagHelperRunner

-0.50

fillType

-0.49

enumi

-0.48

aarrggbb

-0.47

AnchorStyles

-0.45

ِّف

-0.45

POSITIVE LOGITS

끗

0.57

 utafitiHapana

0.53

MessageOf

0.53

duled

0.52

 Viana

0.49

 télécommande

0.49

ITUD

0.48

 rubbed

0.47

 للمعارف

0.46

 culturale

0.46

Activations Density 0.373%

sequences of alphanumeric characters representing data structures or commands

No Comments

No Known Activations