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

collection

-0.72

taker

-0.69

 Disciple

-0.66

Bor

-0.66

yu

-0.63

pher

-0.63

tsky

-0.61

yah

-0.61

 Committees

-0.61

puff

-0.61

POSITIVE LOGITS

 Meier

0.73

icum

0.68

ocular

0.67

nox

0.67

dimension

0.66

²¾

0.64

ihilation

0.64

antha

0.63

 careers

0.63

 grap

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.