INDEX

Explanations

terms related to various organizations and professional fields, such as cultural councils, clinical training, and awards

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>

-1.50

 onPause

-0.69

ksikon

-0.66

<?

-0.63

 الأمريكي

-0.63

govine

-0.63

 січня

-0.62

 onStop

-0.61

ربای

-0.60

amerikan

-0.60

POSITIVE LOGITS

 quoique

1.63

 affor

1.57

 accla

1.55

 maneu

1.53

 quelquefois

1.46

 impra

1.45

 véhic

1.45

 tantôt

1.42

 reluct

1.42

 fortn

1.39

Activations Density 1.454%

terms related to various organizations and professional fields, such as cultural councils, clinical training, and awards

No Comments

No Known Activations