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

soDeliveryDate

-0.91

inators

-0.71

Newsletter

-0.69

 Wolver

-0.68

adem

-0.66

apesh

-0.65

hh

-0.65

Cs

-0.64

%%

-0.63

 Surviv

-0.62

POSITIVE LOGITS

Cole

0.63

 awaited

0.62

 privileged

0.62

 probable

0.62

avia

0.61

oled

0.61

 orderly

0.60

 eagerly

0.59

CVE

0.59

 suspected

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.