INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

tree

-0.68

Psy

-0.66

 malt

-0.64

[+

-0.64

POW

-0.61

dragon

-0.61

âĻ¦

-0.61

growth

-0.60

Wax

-0.60

amd

-0.60

POSITIVE LOGITS

 neighbours

0.69

NEC

0.68

perse

0.68

notations

0.67

Ire

0.66

 Meier

0.66

brids

0.66

encing

0.64

 Associates

0.64

ilater

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.