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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 transformer

-0.79

translation

-0.77

 redes

-0.66

fficient

-0.65

ebook

-0.64

pg

-0.63

 localized

-0.61

 Publication

-0.61

review

-0.61

alam

-0.60

POSITIVE LOGITS

 quotas

0.76

mares

0.72

Nap

0.68

Ce

0.68

Í

0.67

idges

0.67

enment

0.67

 ceilings

0.65

Ops

0.64

zinski

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.