INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

etheless

-0.94

ciating

-0.84

 destro

-0.77

 exha

-0.74

 lapt

-0.71

HQ

-0.70

 professionalism

-0.69

 circumstance

-0.68

 millenn

-0.68

 Bulg

-0.66

POSITIVE LOGITS

velt

0.89

morph

0.77

ortment

0.75

ridges

0.70

][

0.66

ences

0.65

 Hopkins

0.65

 Distribut

0.65

ixture

0.64

ires

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.