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

seed

-0.72

owski

-0.71

 inspected

-0.68

oulos

-0.67

resist

-0.67

 crush

-0.64

amia

-0.63

ulous

-0.62

icum

-0.61

oka

-0.61

POSITIVE LOGITS

 GOODMAN

0.69

 showc

0.67

addons

0.67

 glim

0.66

EGIN

0.65

 midfield

0.64

features

0.63

 lineback

0.61

ilities

0.61

IRE

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.