INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

conservancy

-0.77

elist

-0.73

iary

-0.66

 fundraiser

-0.65

 constraint

-0.65

yip

-0.65

 selling

-0.63

 login

-0.62

 begging

-0.62

essage

-0.62

POSITIVE LOGITS

 Beir

0.91

MRI

0.71

duc

0.71

ctive

0.68

 Leban

0.67

tainment

0.66

 Deaths

0.66

BUR

0.66

herty

0.66

 Manz

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.