INDEX

Explanations

modals expressing obligation or possibility, particularly in relation to difficulties and social responsibilities

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>

-1.89

 intersper

-0.92

 quitted

-0.81

-0.78

 endow

-0.77

 amass

-0.77

 vainly

-0.76

 vanqu

-0.75

 forbear

-0.75

/**

-0.71

POSITIVE LOGITS

 Deber

0.83

 Più

0.80

should

0.78

 Perché

0.77

 Luglio

0.75

 Should

0.74

Should

0.73

cautionary

0.72

 Altri

0.72

 Giugno

0.71

Activations Density 0.297%

modals expressing obligation or possibility, particularly in relation to difficulties and social responsibilities

No Comments

No Known Activations