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

ppy

-0.73

limit

-0.72

ICO

-0.67

Americ

-0.65

check

-0.64

/+

-0.64

 Chase

-0.63

EST

-0.62

shore

-0.61

esty

-0.60

POSITIVE LOGITS

 millenn

0.94

uala

0.87

awaru

0.79

dinand

0.76

negie

0.72

ħĭ

0.72

 elector

0.72

 adolesc

0.72

ikhail

0.70

 notor

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.