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

Negative Logits

ayers

-0.78

pees

-0.72

theless

-0.67

BLE

-0.67

agall

-0.66

BILITY

-0.65

rake

-0.62

afort

-0.61

 strut

-0.61

 understatement

-0.61

POSITIVE LOGITS

pox

0.77

lov

0.71

oslav

0.71

Pax

0.70

aeper

0.69

rov

0.66

iatus

0.65

near

0.64

Zone

0.64

ivia

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.