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

vae

-0.89

yz

-0.70

roud

-0.70

 Hancock

-0.70

rament

-0.69

hei

-0.69

mn

-0.67

plom

-0.67

zx

-0.67

ointed

-0.66

POSITIVE LOGITS

 flashbacks

0.80

Fou

0.77

advertising

0.75

baum

0.70

 Rats

0.70

 Archdemon

0.69

 Drugs

0.69

LINE

0.65

ocard

0.64

Newsletter

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.