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

 Dominic

-0.62

DCS

-0.62

-0.61

 transplant

-0.61

 Gardens

-0.61

 Selection

-0.60

 inheritance

-0.58

 Controller

-0.58

 Variety

-0.58

POSITIVE LOGITS

 complied

0.71

atonin

0.71

TPPStreamerBot

0.68

emonium

0.68

itals

0.68

llor

0.67

iners

0.64

orget

0.62

ija

0.62

 vigorously

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.