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

pled

-0.74

AGES

-0.70

requisite

-0.69

Oracle

-0.67

 lining

-0.66

verbal

-0.65

ulously

-0.64

verse

-0.63

ching

-0.63

hers

-0.62

POSITIVE LOGITS

eq

0.76

wana

0.71

 miscon

0.70

ivity

0.69

heid

0.69

 Progress

0.69

ignty

0.67

 Jericho

0.67

 Brands

0.67

 vape

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.