INDEX

Explanations

mentions of bodily waste or related activities

oai_token-act-pair · gpt-3.5-turbo

terms related to bodily functions, specifically urination and defecation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Flavoring

-0.94

aido

-0.79

pdf

-0.75

attribute

-0.71

HCR

-0.70

arya

-0.70

 BaseType

-0.70

ICA

-0.69

*/(

-0.67

cffffcc

-0.66

POSITIVE LOGITS

pee

1.19

pee

1.17

 bladder

0.89

pees

0.88

 ejac

0.78

 thirsty

0.78

 flush

0.78

ur

0.77

 empt

0.76

 baths

0.75

Activations Density 0.014%

mentions of bodily waste or related activities

terms related to bodily functions, specifically urination and defecation

No Comments

No Known Activations