INDEX

Explanations

personal thoughts and emotions expressed in a somewhat scattered and disjointed manner

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

 massacres

-1.02

 disinformation

-0.96

 atrocities

-0.95

 traitors

-0.94

so

-0.94

 bombings

-0.94

 also

-0.94

 mismanagement

-0.93

 insurgents

-0.93

-0.91

POSITIVE LOGITS

<bos>

16.48

 dispen

2.81

expandindo

2.79

GEBURTSDATUM

2.77

 betweenstory

2.64

 Administrativna

2.55

Autoritní

2.51

 effe

2.48

تقاوى

2.48

 !...

2.46

Activations Density 0.173%

personal thoughts and emotions expressed in a somewhat scattered and disjointed manner

No Comments

No Known Activations