INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

oÄŁ

-0.62

ettings

-0.62

 tremend

-0.61

Pul

-0.60

 Polk

-0.60

 Vaugh

-0.59

idon

-0.59

 waking

-0.59

itol

-0.58

Ã¯ve

-0.57

POSITIVE LOGITS

CVE

0.73

ullivan

0.67

 certs

0.66

chrom

0.63

zos

0.62

una

0.62

 Caption

0.61

 Website

0.58

$$$$

0.57

 ACTIONS

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.