INDEX

Explanations

the word "or" in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.12.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>

-1.85

 SEDS

-0.82

FunctionFlags

-0.70

//////////////

-0.64

UTF

-0.63

apnews

-0.62

 pola

-0.61

 ***!

-0.61

////////////

-0.61

Denomin

-0.60

POSITIVE LOGITS

 disagre

1.74

 shenan

1.64

 gaily

1.64

 milf

1.63

 apprehen

1.63

 maneu

1.62

 accla

1.55

 impra

1.54

 increa

1.52

 reluct

1.51

Activations Density 0.303%

the word "or" in various contexts

No Comments

No Known Activations