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

 dehyd

-0.72

igslist

-0.68

 Ribbon

-0.68

omore

-0.68

ected

-0.67

izontal

-0.66

xit

-0.63

iban

-0.63

izont

-0.63

itored

-0.62

POSITIVE LOGITS

ince

0.76

iners

0.72

iability

0.71

à¥

0.68

 invested

0.65

itech

0.63

Tot

0.62

ica

0.61

 Angelo

0.60

æĦ

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.