INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

å¥³

-0.71

inki

-0.70

usalem

-0.68

plet

-0.67

weed

-0.67

olit

-0.67

å°Ĩ

-0.65

kefeller

-0.64

ppe

-0.63

llular

-0.63

POSITIVE LOGITS

ado

0.71

 Span

0.71

Sav

0.64

bones

0.62

haz

0.61

 Cortex

0.61

Scot

0.60

 beams

0.60

 Gonz

0.59

 Marketable

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.