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

ophile

-0.79

oths

-0.78

omorphic

-0.71

ovie

-0.71

laus

-0.71

opoly

-0.70

opol

-0.67

uits

-0.67

arov

-0.66

haps

-0.66

POSITIVE LOGITS

 rejection

0.73

SourceFile

0.72

 nausea

0.65

McA

0.64

rast

0.62

 abdom

0.62

 amplification

0.62

nce

0.60

 expectation

0.60

ãĤ¼ãĤ¦ãĤ¹

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.