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

 Veter

-0.74

teness

-0.73

rities

-0.70

ilts

-0.69

BLIC

-0.69

ULTS

-0.69

quickShipAvailable

-0.68

 IMAGES

-0.68

ASON

-0.66

Desk

-0.66

POSITIVE LOGITS

 pardon

0.78

 slate

0.69

apolis

0.65

 appellate

0.64

oton

0.63

otom

0.62

 treat

0.62

alli

0.62

 convertible

0.62

 wills

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.