INDEX

Explanations

terms related to computer security threats, specifically focused on trojans

oai_token-act-pair · gpt-3.5-turbo

references to digital security threats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ulse

-0.83

wives

-0.80

ģ«

-0.76

IELD

-0.74

maxwell

-0.70

Ļ½

-0.69

elo

-0.67

rentices

-0.64

wife

-0.63

rator

-0.62

POSITIVE LOGITS

tro

1.20

tted

0.97

dden

0.84

tsky

0.81

toe

0.81

oidal

0.80

isure

0.78

teenth

0.75

tto

0.71

bled

0.70

Activations Density 0.023%

terms related to computer security threats, specifically focused on trojans

references to digital security threats

No Comments

No Known Activations