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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ĪĴ

-0.72

metic

-0.69

igmatic

-0.68

task

-0.66

holes

-0.63

ticket

-0.62

checking

-0.62

infeld

-0.62

emer

-0.61

Murray

-0.61

POSITIVE LOGITS

ariat

0.82

kefeller

0.75

[+

0.73

osa

0.73

ulz

0.73

ohyd

0.73

 Cells

0.71

oodle

0.70

ardless

0.67

roxy

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.