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

Optional

-0.74

âĶĢâĶĢ

-0.72

ATER

-0.71

soDeliveryDate

-0.69

 apostle

-0.69

 Apostle

-0.69

 glim

-0.67

 Scrolls

-0.67

 Scripture

-0.66

 Sorceress

-0.65

POSITIVE LOGITS

eatures

0.88

cutting

0.80

seys

0.76

cuts

0.73

healthy

0.72

emaker

0.70

 ceilings

0.69

aware

0.68

norm

0.66

heastern

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.