INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

itÃ©

-0.77

Downloadha

-0.70

osponsors

-0.70

 pathogens

-0.67

ãĥĸ

-0.66

ogens

-0.64

ktop

-0.63

 capt

-0.63

ichick

-0.63

igue

-0.61

POSITIVE LOGITS

dimension

0.76

 Direction

0.74

Construction

0.71

stice

0.69

 direction

0.68

ray

0.68

reads

0.67

Rail

0.67

etsy

0.67

AR

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.