INDEX

Explanations

comments and documentation in code, particularly those marked with asterisks

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

bieron

-0.51

الحياه

-0.46

politan

-0.44

ձ

-0.43

hide

-0.42

vejte

-0.42

 acciaio

-0.42

末

-0.41

SaveChangesAsync

-0.41

 vantaggi

-0.41

POSITIVE LOGITS

ftagPool

0.82

SourceChecksum

0.80

 Signalez

0.79

RenderAtEndOf

0.76

 NSCoder

0.71

 InputDecoration

0.69

UserScript

0.69

GEBURTSDATUM

0.68

();)

0.66

 дописавши

0.65

Activations Density 0.055%

comments and documentation in code, particularly those marked with asterisks

No Comments

No Known Activations