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

kus

-1.05

aber

-0.75

Hung

-0.73

fee

-0.72

aum

-0.71

spons

-0.70

 newcom

-0.69

 senses

-0.69

usalem

-0.69

ventures

-0.68

POSITIVE LOGITS

odon

0.77

 Chic

0.68

 Hath

0.66

 pave

0.63

-+-+-+-+

0.62

broken

0.62

 Izan

0.61

otos

0.61

 Weston

0.61

 intersections

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.