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

 telev

-0.77

ements

-0.70

 laun

-0.69

 perfected

-0.69

odcast

-0.67

 pioneered

-0.67

ibaba

-0.64

MSN

-0.63

NetMessage

-0.63

vered

-0.63

POSITIVE LOGITS

iary

0.77

 Sands

0.77

trace

0.66

 Â¯

0.65

robe

0.65

¶ħ

0.65

 Scot

0.63

team

0.62

nery

0.62

 CONS

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.