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

 Crunch

-0.76

éĹĺ

-0.74

URI

-0.72

rame

-0.71

IDENT

-0.70

 restraint

-0.70

Ä

-0.67

 Battlefield

-0.67

 tsunami

-0.63

NAT

-0.62

POSITIVE LOGITS

oyd

0.74

gs

0.73

 thru

0.68

ibn

0.66

dated

0.65

////////////////

0.65

////////

0.65

lly

0.63

++++++++++++++++

0.63

areth

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.