INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

idine

-0.84

uga

-0.83

eness

-0.80

oud

-0.80

izons

-0.77

iov

-0.75

anium

-0.75

dinand

-0.75

utters

-0.73

aki

-0.73

POSITIVE LOGITS

*:

0.82

 Logged

0.79

 Posts

0.76

TBD

0.73

${

0.72

:[

0.71

âĢİ

0.70

 Boxing

0.70

 âĨĳ

0.69

!:

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.