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

pac

-0.81

Pac

-0.75

 Lindsey

-0.71

PAC

-0.65

TW

-0.64

ilipp

-0.64

Cyn

-0.64

Wr

-0.62

Ari

-0.62

Domin

-0.62

POSITIVE LOGITS

aceae

0.77

 mushroom

0.69

 redes

0.69

 brim

0.68

©¶æ

0.66

 harvest

0.66

 franch

0.65

actory

0.64

raid

0.63

 municip

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.