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

 Surv

-0.70

jen

-0.69

 Cont

-0.68

:[

-0.64

arthed

-0.64

 delaying

-0.62

 Likely

-0.61

 Deadly

-0.61

radius

-0.60

 deploying

-0.60

POSITIVE LOGITS

agall

0.86

DAQ

0.78

 slots

0.68

igure

0.66

osher

0.66

legraph

0.65

EStreamFrame

0.65

 hats

0.65

ait

0.64

intosh

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.