INDEX

Explanations

Quotation marks and dialogue within the text

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

chanind/openwebtext-gemma

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

ctigges/openwebtext-gemma-1024-cl

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.31

ⓧ

-0.90

 springfox

-0.82

 дописавши

-0.73

<?

-0.73

EndGlobalSection

-0.68

/***

-0.67

 Roskov

-0.67

FunctionFlags

-0.66

EndProject

-0.65

POSITIVE LOGITS

 unspeak

1.51

 reluct

1.48

 apprehen

1.44

 disagre

1.43

 increa

1.39

 accla

1.36

 tolerably

1.33

 affor

1.33

 gaily

1.31

 maneu

1.31

Activations Density 0.202%

Quotation marks and dialogue within the text

No Comments

No Known Activations