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

 Bulg

-0.98

 Seym

-0.82

 Saur

-0.81

mble

-0.76

 Bened

-0.70

 Hanna

-0.69

 Adin

-0.67

wave

-0.67

 Faul

-0.66

 Hayden

-0.66

POSITIVE LOGITS

 guiActiveUn

0.80

uyomi

0.78

 ethic

0.75

 polic

0.74

 counters

0.73

tnc

0.70

itbart

0.69

displayText

0.68

 occup

0.67

 emphasis

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.