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

nces

-0.80

sth

-0.68

uffer

-0.67

pak

-0.65

lled

-0.64

atari

-0.64

itative

-0.64

aked

-0.63

kok

-0.63

ako

-0.63

POSITIVE LOGITS

0.82

iated

0.74

 Uriel

0.68

 Mehran

0.67

iation

0.65

iating

0.65

iator

0.64

 Vector

0.63

emort

0.63

iations

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.