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

SPONSORED

-1.03

yss

-0.91

icum

-0.85

é¾

-0.83

icrobial

-0.82

å§«

-0.80

etheless

-0.76

perty

-0.72

ias

-0.71

ospital

-0.71

POSITIVE LOGITS

 precon

0.66

bul

0.64

 bankrupt

0.63

 hesitate

0.63

vap

0.62

 irrational

0.62

 arbitrarily

0.62

opian

0.62

 duty

0.61

 extrad

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.