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

 neutron

-0.75

 assert

-0.74

 rall

-0.73

 affirmation

-0.66

 neigh

-0.66

 tenancy

-0.65

LIA

-0.64

 affirm

-0.64

 cultivation

-0.63

Sah

-0.63

POSITIVE LOGITS

hov

0.81

UTF

0.80

ouls

0.79

dylib

0.77

nel

0.76

orts

0.76

phies

0.75

kamp

0.75

iform

0.75

arrow

0.74

Activations Density 0.000%

No Known Activations

This feature has no known activations.