INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

PsyNetMessage

-0.84

fare

-0.74

atform

-0.73

 Ares

-0.72

EVA

-0.69

\\\\\\\\

-0.69

atics

-0.67

INESS

-0.67

 Artemis

-0.67

ADS

-0.67

POSITIVE LOGITS

 Shut

0.62

 Liter

0.61

liter

0.60

 THANK

0.59

limits

0.59

 Authorities

0.58

 belongs

0.57

 WRITE

0.57

 punishable

0.57

vacc

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.