INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

orian

-0.76

uthor

-0.61

taker

-0.61

 Wouldn

-0.61

urus

-0.60

spo

-0.59

iframe

-0.58

Harris

-0.58

}}}

-0.57

Lot

-0.57

POSITIVE LOGITS

 resil

0.83

 Regions

0.71

icago

0.70

 retri

0.67

AUT

0.66

 arri

0.66

Alm

0.64

 ancest

0.63

 mathemat

0.63

 neighb

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.