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

stress

-0.73

quart

-0.70

iry

-0.67

issue

-0.67

ãĥ¤

-0.65

icken

-0.61

erc

-0.61

 tabl

-0.61

 quart

-0.60

agen

-0.59

POSITIVE LOGITS

matically

0.69

ewater

0.69

NetMessage

0.67

 Account

0.67

pload

0.67

 Demand

0.66

arbon

0.64

idon

0.64

 Policies

0.63

 Parking

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.