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

ril

-0.73

rils

-0.72

amn

-0.69

omore

-0.67

anie

-0.67

isphere

-0.66

igi

-0.65

rontal

-0.65

seys

-0.64

imeters

-0.64

POSITIVE LOGITS

 blat

0.77

0.71

 undone

0.68

 sauces

0.67

 Pricing

0.63

 reluct

0.62

ware

0.61

liquid

0.61

0.60

tested

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.