INDEX

Explanations

expressions of desire, need, and intention

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

EReference

-0.37

Tradition

-0.36

<bos>

-0.36

ècie

-0.35

 đơn

-0.34

 dripping

-0.34

 FACILITY

-0.34

Preced

-0.33

ú

-0.33

 tradition

-0.33

POSITIVE LOGITS

 beginnetje

0.70

DockStyle

0.63

OCCURRED

0.55

styleable

0.54

IUrlHelper

0.53

ViewFeatures

0.53

CppMethod

0.52

ValueStyle

0.50

PreferredItem

0.49

ModelAdmin

0.48

Activations Density 0.287%

expressions of desire, need, and intention

No Comments

No Known Activations