INDEX

Explanations

references to figures, files, and declarations of conflicts of interest

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

 Clow

-0.50

scalatest

-0.50

 thofe

-0.49

 caufe

-0.48

ential

-0.46

felves

-0.46

rafat

-0.44

lüğ

-0.44

detto

-0.43

MouseEvent

-0.43

POSITIVE LOGITS

ContentAsync

0.83

//

0.76

MLLoader

0.74

 propOrder

0.72

 gynhyrchwyd

0.71

0.68

 跳转至

0.67

RenderAtEndOf

0.67

 EconPapers

0.66

>",

0.65

Activations Density 1.157%

references to figures, files, and declarations of conflicts of interest

No Comments

No Known Activations