INDEX

Explanations

terms and structures related to programming and technical specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

aktery

-0.69

ⓧ

-0.67

 nargin

-0.65

enterOuterAlt

-0.65

imageshack

-0.63

 BoxDecoration

-0.62

 Italijani

-0.62

gonic

-0.61

UTERS

-0.60

หาย

-0.60

POSITIVE LOGITS

</tbody>

0.56

ost

0.56

 makl

0.53

 Shah

0.52

wit

0.51

hoeddwyd

0.50

味

0.50

vit

0.49

tanleria

0.49

 permitan

0.48

Activations Density 2.868%

terms and structures related to programming and technical specifications

No Comments

No Known Activations