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

oner

-0.75

oller

-0.75

omer

-0.73

edin

-0.69

aminer

-0.65

ortal

-0.64

idate

-0.64

ball

-0.64

morph

-0.63

Phys

-0.63

POSITIVE LOGITS

 metic

0.73

 racks

0.71

 preparations

0.69

 queues

0.68

 exhib

0.68

 jewels

0.67

 Nile

0.66

 Bengal

0.66

 Warsaw

0.65

iors

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.