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

ema

-0.85

eco

-0.82

baugh

-0.82

raw

-0.81

aan

-0.79

rawl

-0.79

ongo

-0.76

ugg

-0.73

 Crew

-0.72

undown

-0.72

POSITIVE LOGITS

 Glas

0.71

 Roose

0.70

 ampl

0.70

 Huck

0.68

 magn

0.66

 Democr

0.63

 beams

0.63

 Amen

0.63

 Carnegie

0.63

 respons

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.