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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 PsyNet

-0.85

INESS

-0.84

FTWARE

-0.83

STEM

-0.80

ME

-0.74

ipple

-0.72

Availability

-0.72

ospace

-0.71

TPS

-0.67

holes

-0.67

POSITIVE LOGITS

las

0.77

tyr

0.73

 Reborn

0.72

 diction

0.71

 borrowed

0.69

ysis

0.69

 probation

0.69

 baggage

0.67

 parole

0.67

 billboards

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.