INDEX

Explanations

derogatory terms or insults

oai_token-act-pair · gpt-3.5-turbo

derogatory labels or insults directed at individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 deliberations

-0.77

 transitions

-0.75

anticipated

-0.70

 Flavoring

-0.70

knit

-0.70

 unfolding

-0.70

irtual

-0.68

ortality

-0.68

ersive

-0.68

 Extended

-0.66

POSITIVE LOGITS

 liar

1.56

 traitor

1.38

 hypocr

1.33

 bigot

1.32

 whore

1.28

 rapist

1.23

 coward

1.19

 racists

1.19

 racist

1.18

fascist

1.17

Activations Density 0.393%

derogatory terms or insults

derogatory labels or insults directed at individuals

No Comments

No Known Activations