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

guard

-0.93

pill

-0.89

pillar

-0.76

imon

-0.75

indust

-0.73

orph

-0.72

lon

-0.71

mon

-0.69

Gri

-0.68

syn

-0.68

POSITIVE LOGITS

ï¿½ï¿½

0.84

 nomine

0.75

 whoever

0.69

 Mandela

0.67

0.66

NetMessage

0.66

 secondly

0.66

 thinker

0.63

ablishment

0.63

terson

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.