INDEX

Explanations

mentions of specific brands such as "Norton" and "mantec."

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

 intersper

-1.10

 unspeak

-1.02

 apprehen

-0.95

 maneu

-0.90

 unden

-0.89

 encomp

-0.89

 milf

-0.88

 gaily

-0.88

 witcher

-0.88

 intermitt

-0.86

POSITIVE LOGITS

‚

0.86

 للاسماء

0.81

Danny

0.73

 Danny

0.71

 insuffisamment

0.66

+#+

0.65

 Roskov

0.63

 تانيه

0.63

حياتها

0.62

expandindo

0.62

Activations Density 0.720%

mentions of specific brands such as "Norton" and "mantec."

No Comments

No Known Activations