INDEX

Explanations

mentions of specific types of lenses

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>

-2.47

 intersper

-1.22

-0.91

 endeavored

-0.91

 underval

-0.88

ⓧ

-0.87

 endeavoured

-0.85

 quitted

-0.85

 vainly

-0.85

 acquaint

-0.84

POSITIVE LOGITS

 Lens

1.48

 lens

1.43

Lens

1.42

 lenses

1.28

lens

1.27

 Lenses

1.27

 bicic

0.88

 jawa

0.74

 Minang

0.70

 borsa

0.70

Activations Density 0.088%

mentions of specific types of lenses

No Comments

No Known Activations