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

 acquisitions

-0.77

 tradem

-0.68

lique

-0.68

clamation

-0.66

ule

-0.66

itures

-0.63

 kinderg

-0.63

mint

-0.62

ought

-0.61

 tokens

-0.61

POSITIVE LOGITS

 Canaver

0.74

aurus

0.71

onica

0.65

 Files

0.62

 DEAD

0.61

 McCartney

0.61

 Krist

0.61

NRS

0.60

 STAND

0.60

Hav

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.