INDEX

Explanations

negative descriptors associated with harmful or immoral actions

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>

-2.73

HasColumnType

-0.97

ApiModelProperty

-0.82

CreateMap

-0.79

lateinit

-0.76

flex

-0.76

addComponent

-0.76

IsRequired

-0.76

AllowUser

-0.76

 createState

-0.75

POSITIVE LOGITS

 napoli

1.86

 Minang

1.82

 frankfurt

1.81

Juf

1.77

 stockholm

1.73

 bandung

1.71

 ecru

1.70

 milano

1.68

 toledo

1.67

 tramont

1.67

Activations Density 0.206%

negative descriptors associated with harmful or immoral actions

No Comments

No Known Activations