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

Peb

-0.87

âĸ¬

-0.82

NFC

-0.79

anamo

-0.75

NX

-0.70

agate

-0.69

rg

-0.69

 ripe

-0.68

Chu

-0.68

amaru

-0.67

POSITIVE LOGITS

eeper

0.69

 expressive

0.67

fet

0.66

hum

0.64

nas

0.63

idon

0.63

 differential

0.62

 bell

0.62

 basin

0.62

sis

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.