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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

maxwell

-0.89

mer

-0.69

ME

-0.69

"},{"

-0.67

NEY

-0.67

orders

-0.67

iversity

-0.66

"}],"

-0.65

 Cosponsors

-0.65

ARDS

-0.65

POSITIVE LOGITS

é¾įå

0.71

 roommate

0.64

 adoptive

0.64

ovi

0.62

 organizational

0.61

 Immortal

0.61

 induct

0.60

ppelin

0.60

 alumni

0.60

IU

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.