INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

arthed

-0.92

soDeliveryDate

-0.82

duc

-0.76

intendent

-0.71

NV

-0.66

ilda

-0.64

 Democr

-0.64

nn

-0.63

Rated

-0.63

NCT

-0.62

POSITIVE LOGITS

 canv

0.63

 ticking

0.62

sum

0.62

 stage

0.62

 stocking

0.61

*/(

0.60

 clinically

0.59

 kettle

0.59

culosis

0.59

ournals

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.