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

Sov

-0.77

destruct

-0.76

nown

-0.72

pmwiki

-0.70

rez

-0.69

azi

-0.69

ainer

-0.68

Äĩ

-0.67

accompanied

-0.67

onna

-0.66

POSITIVE LOGITS

Ĥ¬

0.67

 Webb

0.64

Rez

0.62

 Macy

0.61

 Hodg

0.61

 shopping

0.61

 actionGroup

0.60

 Shoot

0.60

 Receiver

0.60

Alert

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.