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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ews

-0.70

»Ĵ

-0.67

elight

-0.67

earable

-0.66

onite

-0.65

orns

-0.65

antry

-0.64

alla

-0.64

 appre

-0.64

rients

-0.64

POSITIVE LOGITS

 Townsend

0.74

 Vaughan

0.67

Quantity

0.61

resident

0.60

BuyableInstoreAndOnline

0.59

 clearance

0.58

UA

0.58

/-

0.57

 alike

0.57

 Mill

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.