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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Mari

-0.79

qi

-0.75

port

-0.74

gio

-0.68

cious

-0.67

 flag

-0.67

ports

-0.66

mith

-0.66

 Lama

-0.65

edi

-0.64

POSITIVE LOGITS

thumbnails

0.78

ãĥ¼ãĥĨ

0.75

ISON

0.74

 COURT

0.65

ANC

0.64

 VIDE

0.63

channelAvailability

0.63

REAM

0.62

Daddy

0.61

AIR

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.