INDEX

Explanations

patterns related to data structures and their representations

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

node[above] edge[bend]

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

findpost

-0.71

GEBURTSDATUM

-0.55

drawSprites

-0.47

Autoritní

-0.44

ProgressHUD

-0.42

MessageOf

-0.39

BeginContext

-0.39

AutoresizingMask

-0.38

MLLoader

-0.38

 newBuilder

-0.38

POSITIVE LOGITS

 kaarangay

0.64

ьаж

0.58

endpush

0.46

észetes

0.45

 Мексичка

0.43

__;

0.42

 olev

0.42

 klima

0.42

FontStyle

0.42

$_['

0.41

Activations Density 0.055%

patterns related to data structures and their representations

node[above] edge[bend]

No Comments

No Known Activations