INDEX

Explanations

terms related to ice sports, specifically hockey

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.0.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>

-0.88

ve

-0.67

be

-0.66

 continue

-0.66

set

-0.65

 also

-0.65

struct

-0.65

switch

-0.65

POSITIVE LOGITS

 Hockey

1.82

 hockey

1.79

Hockey

1.76

hockey

1.70

 effe

1.63

 stockholm

1.63

 maneu

1.62

 increa

1.61

 strick

1.59

 embodi

1.56

Activations Density 0.168%

terms related to ice sports, specifically hockey

No Comments

No Known Activations