INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ameless

-0.70

edom

-0.69

ensibly

-0.69

vity

-0.68

OUP

-0.68

pez

-0.68

anwhile

-0.67

uador

-0.66

glomer

-0.65

apest

-0.65

POSITIVE LOGITS

Rim

0.68

MpServer

0.66

ding

0.66

bos

0.64

 Cree

0.63

PID

0.62

âĦ¢:

0.62

Dial

0.60

IOR

0.60

 counterparts

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.