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

Sov

-0.71

 crumble

-0.62

ussian

-0.62

utsche

-0.61

 councils

-0.60

daq

-0.59

illin

-0.59

 Confederacy

-0.58

pd

-0.58

Dul

-0.56

POSITIVE LOGITS

jp

0.70

Roberts

0.69

ACA

0.65

 Canaver

0.64

HI

0.64

 Bennett

0.64

alos

0.64

ordan

0.64

EXP

0.64

packing

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.