INDEX

Explanations

terms related to sexual activities and practices

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

chanind/openwebtext-gemma

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

ctigges/openwebtext-gemma-1024-cl

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.88

 autorytatywna

-0.81

/*---

-0.72

 AssemblyCompany

-0.71

MockBean

-0.71

UnknownFields

-0.70

echo

-0.70

Autoritní

-0.69

 Normdatei

-0.69

 Shetterly

-0.68

POSITIVE LOGITS

 ecru

1.96

 gaily

1.85

 unspeak

1.82

 disagre

1.80

 pymysql

1.79

 swarovski

1.75

 impra

1.70

 tolerably

1.68

 increa

1.65

 reluct

1.63

Activations Density 0.179%

terms related to sexual activities and practices

No Comments

No Known Activations