INDEX

Explanations

profane language

oai_token-act-pair · gpt-3.5-turbo

exclamatory and profane expressions of frustration or anger

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 rece

-0.68

obook

-0.68

uchin

-0.64

 obser

-0.64

HCR

-0.64

Interstitial

-0.63

dfx

-0.62

ioxide

-0.62

oult

-0.62

uries

-0.60

POSITIVE LOGITS

wit

0.97

drivers

0.95

driver

0.94

yeah

0.94

nuts

0.93

ery

0.91

holes

0.90

fuck

0.89

 yeah

0.89

ers

0.88

Activations Density 0.035%

profane language

exclamatory and profane expressions of frustration or anger

No Comments

No Known Activations