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

ACA

-0.87

RAFT

-0.77

OF

-0.75

 breath

-0.69

orers

-0.66

 Stores

-0.66

BP

-0.65

sonian

-0.65

HB

-0.64

ooters

-0.64

POSITIVE LOGITS

 yours

0.70

romeda

0.70

gow

0.69

 Ashton

0.68

leck

0.68

 warmed

0.62

Kap

0.62

origin

0.62

 Vengeance

0.61

 surrounding

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.