INDEX

Explanations

legal and procedural terms related to criminal justice

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>

-2.77

 intersper

-1.37

 gratify

-1.01

 hentai

-0.96

/***

-0.96

 endow

-0.93

 encomp

-0.92

 Mlle

-0.89

 shenan

-0.88

 quitted

-0.88

POSITIVE LOGITS

 moza

0.81

 kupa

0.69

pushButton

0.67

koz

0.64

 balon

0.58

']?>

0.58

UITextField

0.57

 bronz

0.56

'];?>

0.56

 detergente

0.56

Activations Density 1.512%

legal and procedural terms related to criminal justice

No Comments

No Known Activations