INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

hower

-0.68

uin

-0.68

 Guantanamo

-0.66

 shortest

-0.66

eport

-0.63

obook

-0.62

":-

-0.62

 backlog

-0.61

 nomine

-0.61

 Knot

-0.60

POSITIVE LOGITS

coins

0.72

UX

0.72

pixel

0.71

umar

0.71

ox

0.69

ATURE

0.69

punk

0.69

oken

0.69

rot

0.67

acts

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.