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

escription

-1.01

rio

-0.73

ependence

-0.70

 retract

-0.68

ipolar

-0.68

 cannabin

-0.67

 millenn

-0.67

worthiness

-0.65

thood

-0.65

 beacon

-0.63

POSITIVE LOGITS

../

0.71

anas

0.71

lings

0.69

ooth

0.69

Interstitial

0.67

endar

0.66

naire

0.66

ixtures

0.65

 Explicit

0.65

ills

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.