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

IGF

-0.81

âĸ¬

-0.77

 rall

-0.70

 Cortex

-0.70

 primer

-0.69

 tiss

-0.67

 Kirin

-0.67

 Ukrain

-0.66

DOD

-0.63

æĸ¹

-0.63

POSITIVE LOGITS

iffe

0.83

rew

0.80

bach

0.77

etts

0.77

ater

0.74

asons

0.72

upe

0.71

arth

0.70

umph

0.70

bidden

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.