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

ãĥ£

-0.67

ãĤĭ

-0.66

 pronouns

-0.65

agic

-0.64

Jou

-0.62

Ras

-0.61

Bri

-0.61

Connector

-0.60

 Sind

-0.60

 petty

-0.59

POSITIVE LOGITS

imb

0.86

kit

0.81

tracks

0.80

scripts

0.72

screen

0.72

kernel

0.70

redo

0.69

marks

0.68

isites

0.67

iesta

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.