INDEX

Explanations

words related to mutation or alteration

oai_token-act-pair · gpt-3.5-turbo

references to mutilation, particularly in the context of female genital mutilation practices

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

 Defenders

-0.85

ACP

-0.74

ħĭ

-0.67

ngth

-0.65

BuyableInstoreAndOnline

-0.65

Â¯Â¯

-0.65

ï¸

-0.64

 hemisphere

-0.63

DragonMagazine

-0.63

ulhu

-0.62

POSITIVE LOGITS

iple

1.12

atis

0.99

rats

0.97

iny

0.95

ations

0.93

agen

0.91

ually

0.89

mut

0.89

ilation

0.89

ilated

0.85

Activations Density 0.010%

words related to mutation or alteration

references to mutilation, particularly in the context of female genital mutilation practices

No Comments

No Known Activations