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

zac

-0.73

haar

-0.72

Fram

-0.70

oris

-0.68

illac

-0.68

haus

-0.67

flix

-0.67

 hers

-0.65

redits

-0.65

Grey

-0.65

POSITIVE LOGITS

 constituent

0.66

isted

0.66

 Eater

0.64

founded

0.64

clusive

0.64

ominated

0.64

cou

0.63

mble

0.63

ovych

0.61

 sacked

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.