INDEX

Explanations

terms related to the concept of penetrating or intrusion

oai_token-act-pair · gpt-3.5-turbo

terms related to penetration or the act of penetrating

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

OTA

-0.79

arb

-0.78

makers

-0.66

usp

-0.64

bind

-0.63

nesota

-0.63

corn

-0.63

avers

-0.63

HCR

-0.62

inn

-0.62

POSITIVE LOGITS

 penetrated

1.16

 penetration

1.10

 penet

1.05

 penetrate

1.03

 penetrating

0.92

 Explorer

0.88

atform

0.78

ipher

0.77

ierce

0.75

tain

0.74

Activations Density 0.035%

terms related to the concept of penetrating or intrusion

terms related to penetration or the act of penetrating

No Comments

No Known Activations