INDEX

Explanations

references to reading applications or services related to e-books

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

MessageTagHelper

-0.74

ValueStyle

-0.70

idopsis

-0.59

HandlerContext

-0.52

 continúas

-0.52

chengladbach

-0.51

ızı

-0.49

曖昧さ回避

-0.48

 mycelium

-0.48

 <=",

-0.46

POSITIVE LOGITS

forRoot

0.67

AnchorStyles

0.59

aarrggbb

0.56

FilterChain

0.56

angering

0.50

 treści

0.50

protoc

0.49

 downloaded

0.48

gencies

0.48

TRIBUN

0.47

Activations Density 0.436%

references to reading applications or services related to e-books

No Comments

No Known Activations