INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

vic

-0.79

VID

-0.73

Wan

-0.72

BIP

-0.70

Cooldown

-0.70

cles

-0.69

Laughs

-0.68

Hub

-0.68

VPN

-0.67

Ire

-0.67

POSITIVE LOGITS

icter

0.80

olor

0.79

 Schr

0.75

 Muller

0.71

atche

0.68

helm

0.68

Byr

0.68

 Pruitt

0.67

ariat

0.67

anwhile

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.