INDEX

Explanations

terms related to malware or cyber attacks

oai_token-act-pair · gpt-3.5-turbo

references to a specific group or entity, particularly "trojan."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

++++++++++++++++

-0.76

hips

-0.75

rentices

-0.74

maxwell

-0.71

ulse

-0.69

urities

-0.69

orship

-0.66

 discriminating

-0.66

UAL

-0.63

ukong

-0.63

POSITIVE LOGITS

tro

1.27

dden

1.08

tted

0.95

tsky

0.95

tro

0.93

oping

0.86

opard

0.80

isure

0.78

estones

0.76

bled

0.75

Activations Density 0.007%

terms related to malware or cyber attacks

references to a specific group or entity, particularly "trojan."

No Comments

No Known Activations