INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ONG

-0.72

OIL

-0.71

ETH

-0.71

 Multiplayer

-0.69

MM

-0.69

 Bots

-0.69

AUD

-0.68

 Continued

-0.67

CG

-0.67

AV

-0.67

POSITIVE LOGITS

ertodd

0.91

heses

0.76

helial

0.74

arcer

0.70

orescent

0.70

idium

0.68

riger

0.68

escent

0.67

 autonom

0.67

itent

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.