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

quest

-0.81

rency

-0.79

imura

-0.78

govtrack

-0.78

burse

-0.74

amiya

-0.73

iage

-0.72

escription

-0.72

agonist

-0.72

ago

-0.71

POSITIVE LOGITS

 relations

0.70

 parity

0.65

STL

0.65

 staff

0.64

 Survey

0.64

 Relations

0.62

 Duration

0.62

ettes

0.62

 Opinion

0.60

vib

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.