INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 helicop

-0.65

cig

-0.62

 prelim

-0.62

agara

-0.61

 holdings

-0.61

 Recomm

-0.61

 filings

-0.61

 hiber

-0.61

dating

-0.60

 filing

-0.60

POSITIVE LOGITS

RAY

0.75

rea

0.75

rey

0.75

ggle

0.70

gency

0.69

reon

0.69

endon

0.67

 Benn

0.64

 Trey

0.64

 Shaun

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.