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

taboola

-0.69

OSED

-0.68

UNCH

-0.68

asus

-0.67

enser

-0.67

ERT

-0.67

RAFT

-0.66

 ported

-0.66

 redes

-0.66

 Firm

-0.65

POSITIVE LOGITS

 Jagu

0.68

²¾

0.67

 Afgh

0.66

song

0.64

 psychiat

0.63

ball

0.63

ocobo

0.62

aband

0.61

ï¸ı

0.61

kered

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.