INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ufact

-0.74

-0.73

{:

-0.71

omorphic

-0.69

Ctrl

-0.66

ADV

-0.64

doms

-0.63

 Amph

-0.62

PLA

-0.62

alsa

-0.61

POSITIVE LOGITS

idity

0.70

ailand

0.66

 Shank

0.65

 waivers

0.62

oard

0.62

 Schiff

0.61

irds

0.61

rush

0.61

 waiver

0.60

aya

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.