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

anova

-0.85

esan

-0.76

 annexation

-0.69

 Aberdeen

-0.68

ifax

-0.68

 Fallon

-0.67

IFA

-0.63

IFIC

-0.61

 Misty

-0.61

 Trafford

-0.61

POSITIVE LOGITS

psc

0.88

 chambers

0.80

cgi

0.74

tube

0.72

geoning

0.67

rop

0.63

 bloodstream

0.63

uti

0.63

 electronics

0.62

 organ

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.