INDEX

Explanations

the word "def" or variations of it: "defected", "defense", or "defined"

oai_token-act-pair · gpt-3.5-turbo

variations of the word "defame" or its derivatives

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

DAY

-0.77

 Dragonbound

-0.72

 Bohem

-0.71

externalActionCode

-0.66

 Madness

-0.66

 Archdemon

-0.65

 Hour

-0.65

 Observatory

-0.65

 Boll

-0.64

[|

-0.64

POSITIVE LOGITS

ensible

1.23

ibr

1.17

erent

1.03

acement

1.02

anged

1.02

erence

0.98

ected

0.98

ident

0.98

aul

0.97

ensions

0.96

Activations Density 0.008%

the word "def" or variations of it: "defected", "defense", or "defined"

variations of the word "defame" or its derivatives

No Comments

No Known Activations