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

ould

-0.73

ourn

-0.65

 sizeof

-0.65

fact

-0.64

conservancy

-0.63

ptions

-0.63

 inval

-0.62

ts

-0.62

 decentral

-0.62

Tot

-0.62

POSITIVE LOGITS

nen

0.73

 Mercenary

0.73

MJ

0.70

ibrary

0.70

Twe

0.69

Wiki

0.68

 Cheney

0.67

renheit

0.66

zzle

0.66

 Roose

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.