INDEX

Explanations

phrases related to witnessing or testifying

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

HuggingFaceFW/fineweb

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.81

<?

-0.81

-0.76

HasAnnotation

-0.75

Související

-0.74

ⓧ

-0.71

contentLoaded

-0.70

-0.67

 EconPapers

-0.66

/***

-0.65

POSITIVE LOGITS

 maneu

1.83

 squa

1.81

 affor

1.79

 impra

1.77

 guarante

1.76

 increa

1.76

aen

1.74

 toledo

1.71

 alre

1.70

 wien

1.69

Activations Density 0.178%

phrases related to witnessing or testifying

No Comments

No Known Activations