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

orth

-0.88

nda

-0.83

xt

-0.78

Param

-0.74

Edited

-0.74

LOD

-0.72

claw

-0.72

Upload

-0.72

IFA

-0.70

lia

-0.69

POSITIVE LOGITS

 same

1.04

 remainder

1.00

 smallest

0.99

 largest

0.95

 lowest

0.91

 earliest

0.91

 fastest

0.90

oret

0.89

 highest

0.88

 rest

0.87

Activations Density 0.000%

No Known Activations

This feature has no known activations.