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

itous

-0.71

obb

-0.70

liest

-0.69

 awarding

-0.65

lying

-0.63

Pwr

-0.61

lished

-0.60

uits

-0.60

ious

-0.60

 plank

-0.58

POSITIVE LOGITS

 antioxid

0.88

HAHA

0.76

ãĥ´

0.72

ensis

0.68

ox

0.67

gaard

0.67

oxin

0.66

 Asgard

0.64

hea

0.63

lust

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.