INDEX

Explanations

mentions of blank items or spaces

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>

-1.66

 Merritt

-0.57

 McGuire

-0.56

-0.54

shed

-0.54

 Khor

-0.52

 McCormack

-0.52

rs

-0.51

 twij

-0.51

Cormack

-0.51

POSITIVE LOGITS

 Blank

1.43

Blank

1.39

 BLANK

1.37

 blank

1.36

 Blan

1.34

Blan

1.33

 blan

1.33

blank

1.32

 blanks

1.26

blan

1.22

Activations Density 0.382%

mentions of blank items or spaces

No Comments

No Known Activations