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

icult

-0.81

lass

-0.73

rentices

-0.65

onge

-0.64

ulas

-0.62

atted

-0.61

 behavi

-0.60

 landlord

-0.60

 fisher

-0.59

ards

-0.59

POSITIVE LOGITS

ãĥ»

0.81

ispers

0.79

Leg

0.75

govtrack

0.73

TBD

0.73

luaj

0.73

iHUD

0.72

 Reloaded

0.70

è£ħ

0.69

 Become

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.