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

 laun

-0.87

WithNo

-0.82

ĸļ

-0.77

interstitial

-0.75

âķĲ

-0.73

ãĥ¯ãĥ³

-0.70

[|

-0.69

-0.67

 Archdemon

-0.67

 Cowboy

-0.67

POSITIVE LOGITS

arr

0.67

pite

0.64

assis

0.61

gg

0.61

ems

0.61

mong

0.61

his

0.60

DoS

0.60

uilding

0.59

mand

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.