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

 largeDownload

-0.82

ĸļ

-0.79

@#&

-0.71

Ô

-0.71

 bonded

-0.71

ortment

-0.67

taboola

-0.65

 replacements

-0.62

 Tradable

-0.62

 bids

-0.62

POSITIVE LOGITS

sr

0.69

lp

0.68

ffen

0.68

ecake

0.68

hp

0.68

blast

0.67

erie

0.67

dp

0.67

cloth

0.64

lake

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.