INDEX

Explanations

numerical values and their occurrences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ruptedException

-0.70

 дописавши

-0.58

fileID

-0.55

MLLoader

-0.54

ggior

-0.54

SuppressLint

-0.53

хьтан

-0.53

stdc

-0.52

 Процитовано

-0.52

 Архів

-0.51

POSITIVE LOGITS

rawDesc

0.83

writeFieldEnd

0.71

SourceChecksum

0.64

 betweenstory

0.58

 heng

0.58

OGND

0.57

landa

0.57

 equipa

0.57

rrggbb

0.57

webElementXpaths

0.56

Activations Density 0.788%

numerical values and their occurrences

No Comments

No Known Activations