INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

anos

-0.70

 Infinity

-0.70

 Pand

-0.69

 lightsaber

-0.68

isman

-0.67

imes

-0.67

 defer

-0.66

 Morales

-0.66

agan

-0.66

obin

-0.65

POSITIVE LOGITS

wx

0.84

wr

0.69

osate

0.67

 squats

0.67

coh

0.65

 Almighty

0.65

 tremend

0.62

gging

0.61

population

0.61

aukee

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.