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

tesy

-0.79

Haunted

-0.79

 redes

-0.77

Ü

-0.75

Ń·

-0.74

iliated

-0.72

earances

-0.70

tions

-0.69

doms

-0.66

IDE

-0.66

POSITIVE LOGITS

 supplement

0.67

 matt

0.64

othing

0.63

mk

0.62

 chamber

0.61

pub

0.60

ris

0.59

 Leilan

0.58

 thirst

0.57

adelphia

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.