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

 choked

-0.70

seless

-0.69

dyl

-0.69

Haunted

-0.69

gotten

-0.67

ieties

-0.66

iances

-0.63

bus

-0.63

blems

-0.62

¶

-0.62

POSITIVE LOGITS

 precursor

0.73

NF

0.72

FP

0.69

ETF

0.69

NL

0.68

[*

0.65

opa

0.64

 breadth

0.63

NP

0.63

gol

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.