INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ilet

-0.77

-0.69

uyomi

-0.68

psey

-0.67

ãĥį

-0.66

igo

-0.65

ItemTracker

-0.64

fell

-0.63

 Hulk

-0.62

 Tube

-0.61

POSITIVE LOGITS

okia

0.66

 dismant

0.63

akes

0.62

Reviewer

0.62

glers

0.60

 Emblem

0.59

keyes

0.58

ubs

0.58

olson

0.58

 Appears

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.