INDEX

Explanations

references to colonies and their relationships to individuals or groups

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>

-2.06

/**

-0.70

Vegeu

-0.68

Comentários

-0.66

 GenerationType

-0.66

HasIndex

-0.66

ProcessEvent

-0.64

Também

-0.64

otheby

-0.63

França

-0.63

POSITIVE LOGITS

 affor

1.92

 unwarran

1.89

 impra

1.87

 pamph

1.81

 unlaw

1.80

 increa

1.78

 disagre

1.75

 hairc

1.73

 reluct

1.72

 unspeak

1.69

Activations Density 0.172%

references to colonies and their relationships to individuals or groups

No Comments

No Known Activations