INDEX

Explanations

keywords related to hacking and technology

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Hack" related to technology and hacking activities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 occas

-0.86

rul

-0.67

 compr

-0.67

ãħĭ

-0.67

 conflic

-0.66

åĬ

-0.65

 markings

-0.64

 confir

-0.62

issance

-0.62

 obser

-0.62

POSITIVE LOGITS

intosh

1.42

athon

1.31

aday

1.13

enberg

1.09

driver

1.01

ett

0.99

lings

0.98

ney

0.94

masters

0.92

drivers

0.90

Activations Density 0.023%

keywords related to hacking and technology

instances of the word "Hack" related to technology and hacking activities

No Comments

No Known Activations