INDEX

Explanations

personal pronouns

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>

-3.48

ⓧ

-1.05

Autoritní

-0.80

GEBURTSDATUM

-0.72

<?

-0.72

PerformLayout

-0.69

дивиду

-0.69

/***

-0.67

expandindo

-0.66

sunami

-0.65

POSITIVE LOGITS

">...

1.03

">/

1.02

 véhic

0.85

:"-

0.84

">“

0.84

 chrysler

0.83

">:

0.79

 hilux

0.78

 soulign

0.78

Fitment

0.77

Activations Density 0.665%

personal pronouns

No Comments

No Known Activations