INDEX

Explanations

phrases related to head and brain injuries

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

Negative Logits

<bos>

-2.06

 intersper

-0.96

/**

-0.82

 quitted

-0.76

 encomp

-0.73

 mustered

-0.73

 renounced

-0.72

 inaugurate

-0.70

ⓧ

-0.70

<?

-0.70

POSITIVE LOGITS

 helmet

0.89

 helmets

0.85

 skull

0.80

 head

0.79

Head

0.77

helmet

0.76

 Head

0.76

Helmet

0.73

 HEAD

0.73

 réjou

0.72

Activations Density 0.235%

phrases related to head and brain injuries

No Known Activations