INDEX

Explanations

references to technical identifiers or codes

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

CppCodeGen

-0.56

MeasureSpec

-0.53

apimachinery

-0.53

MinWidth

-0.49

Secs

-0.47

ictionary

-0.46

'):

-0.45

 series

-0.45

³/

-0.45

 Series

-0.44

POSITIVE LOGITS

endphp

0.60

 betweenstory

0.57

حياته

0.55

styleUrls

0.54

antMatchers

0.54

 Infórmanos

0.54

irited

0.53

resave

0.53

 Stakes

0.50

 AssemblyProduct

0.50

Activations Density 0.129%

references to technical identifiers or codes

No Comments

No Known Activations