INDEX

Explanations

information related to mental health, coping skills, and the risk factors associated with conditions such as depression, stress, and alcoholism

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>

-2.50

 intersper

-1.01

 disambigu

-0.93

 disreg

-0.84

 incarcer

-0.84

 endow

-0.82

 inaugurate

-0.78

 depic

-0.77

 encomp

-0.77

 defray

-0.75

POSITIVE LOGITS

 psicologia

0.97

 balon

0.89

 benzin

0.87

 conflic

0.86

 moza

0.83

 broderie

0.78

 maska

0.77

 kafe

0.74

 ados

0.73

 kaos

0.73

Activations Density 3.159%

information related to mental health, coping skills, and the risk factors associated with conditions such as depression, stress, and alcoholism

No Comments

No Known Activations