INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åħī

-0.69

OSP

-0.67

ECD

-0.64

 regression

-0.64

 Schwarz

-0.61

Graphics

-0.61

GAM

-0.61

ESA

-0.60

ARM

-0.60

ESP

-0.59

POSITIVE LOGITS

ourcing

0.75

eous

0.74

assetsadobe

0.74

abouts

0.68

ĸļ

0.68

 Converted

0.67

ourced

0.66

akin

0.65

obo

0.65

 Machina

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.