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

onite

-0.76

ventions

-0.74

stros

-0.70

rive

-0.69

 upgrade

-0.68

rafted

-0.65

 courtyard

-0.65

oult

-0.65

actor

-0.64

ository

-0.64

POSITIVE LOGITS

>>

0.70

terday

0.67

 Lindsay

0.66

 Lynn

0.64

 Nicotine

0.63

 Kelley

0.62

 Alam

0.62

 Coast

0.61

ILA

0.61

 yawn

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.