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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ghai

-0.91

orsche

-0.90

isu

-0.80

ĸļ

-0.79

mud

-0.76

iphate

-0.74

esville

-0.71

gow

-0.71

ibur

-0.71

smart

-0.70

POSITIVE LOGITS

Eps

0.69

 departures

0.68

 Graves

0.65

 Braun

0.65

 Karn

0.64

 Tenn

0.64

 âĢİ

0.63

Sax

0.63

[+]

0.62

 Osiris

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.