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

uggle

-0.80

 substant

-0.66

ĳå£«

-0.66

 dispar

-0.65

 arrog

-0.64

 uttered

-0.62

 Kardashian

-0.62

 occupant

-0.61

vati

-0.61

 insulted

-0.60

POSITIVE LOGITS

joice

0.77

iterator

0.75

ones

0.70

å£«

0.69

bro

0.67

ohm

0.65

 Wolves

0.63

Motion

0.62

aneous

0.62

ONES

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.