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

 prophetic

-0.68

 listeners

-0.68

cript

-0.68

dyn

-0.66

 christ

-0.66

 histor

-0.65

ovember

-0.63

 homelessness

-0.62

 clergy

-0.61

 audi

-0.60

POSITIVE LOGITS

ice

0.88

ORD

0.75

munition

0.73

drops

0.71

selves

0.71

USE

0.71

dfx

0.71

Uz

0.70

Connector

0.69

REE

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.