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

ename

-0.67

lish

-0.63

à¸

-0.63

ls

-0.62

mable

-0.61

_-

-0.61

eries

-0.59

Tes

-0.59

gs

-0.58

TD

-0.57

POSITIVE LOGITS

afort

0.71

asha

0.68

orsche

0.68

HCR

0.64

missing

0.61

umph

0.60

ophon

0.60

 Ending

0.59

 Contributions

0.59

LOCK

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.