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

catentry

-0.82

ADRA

-0.76

Bie

-0.71

Slot

-0.70

Bow

-0.67

PsyNetMessage

-0.66

Brow

-0.65

Aad

-0.63

Bin

-0.63

Synopsis

-0.63

POSITIVE LOGITS

riors

0.70

arten

0.69

atsuki

0.69

arers

0.68

 aback

0.67

ortunately

0.66

orest

0.66

itus

0.65

 Mechdragon

0.65

nesium

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.