INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 repe

-0.71

define

-0.69

 acqu

-0.68

-0.67

 arri

-0.67

ãģ®é

-0.66

 reven

-0.65

ãĤ´ãĥ³

-0.64

wards

-0.64

faced

-0.63

POSITIVE LOGITS

tsky

0.66

OUNT

0.65

illary

0.64

ulnerability

0.64

orescence

0.63

 cushion

0.63

 Trends

0.62

undown

0.61

pots

0.61

 infectious

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.