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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Pirate

-0.70

 Span

-0.65

oglu

-0.64

 Iceland

-0.63

onym

-0.61

 Onion

-0.61

 Turks

-0.60

abolic

-0.59

 brid

-0.58

ĻĤ

-0.57

POSITIVE LOGITS

ithing

0.73

stru

0.71

 actionGroup

0.69

LET

0.69

numbered

0.69

brace

0.69

mson

0.67

ideshow

0.67

moil

0.67

bus

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.