INDEX

Explanations

sequences of numerical identifiers and formatted data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 kasarigan

-0.76

hésite

-0.66

 Италијани

-0.58

 eins

-0.53

setVerticalGroup

-0.52

Hentet

-0.51

 Emer

-0.50

 đặc

-0.50

itzenden

-0.50

Nazionale

-0.49

POSITIVE LOGITS

onViewCreated

0.62

Hochspringen

0.55

 Napoleonic

0.54

AutoScaleMode

0.53

Спољашње

0.53

qrstuvwxyz

0.52

ihnachts

0.52

</strong>

0.51

اریخ

0.51

XmlAccessType

0.51

Activations Density 0.115%

sequences of numerical identifiers and formatted data structures

No Comments

No Known Activations