INDEX

Explanations

terms related to intrusion, such as intruders, intrusions, and intruder

oai_token-act-pair · gpt-3.5-turbo

terms related to intrusion or unauthorized access

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

creen

-1.02

ndra

-0.86

wagen

-0.82

IELD

-0.80

å§«

-0.78

hare

-0.74

baum

-0.72

BALL

-0.72

hift

-0.72

hirt

-0.71

POSITIVE LOGITS

uders

1.10

uding

1.03

 intr

1.00

ordinary

0.95

inx

0.91

usions

0.89

igent

0.87

uded

0.82

acy

0.82

iencies

0.80

Activations Density 0.020%

terms related to intrusion, such as intruders, intrusions, and intruder

terms related to intrusion or unauthorized access

No Comments

No Known Activations