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

erella

-0.82

endez

-0.79

zzi

-0.79

oven

-0.78

Motor

-0.77

piracy

-0.76

pload

-0.75

ijn

-0.75

chwitz

-0.74

lez

-0.73

POSITIVE LOGITS

 regener

0.69

 aspiration

0.66

 surname

0.65

 tenure

0.63

 suffix

0.61

 Siber

0.61

 Reign

0.60

 extraction

0.60

upl

0.60

 replacement

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.