INDEX

Explanations

dates and events mentioned in the text

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.44

ⓧ

-1.30

/**

-1.12

 quitted

-1.12

<?

-1.10

 intersper

-1.09

-1.02

/***

-1.02

frastructure

-0.88

 forbear

-0.85

POSITIVE LOGITS

ieb

0.62

 Karakter

0.59

 Presenta

0.54

 marea

0.52

 Cerca

0.49

 confec

0.48

 mercad

0.48

Same

0.47

 seksi

0.47

Rng

0.47

Activations Density 2.848%

dates and events mentioned in the text

No Comments

No Known Activations