INDEX

Explanations

terms related to targeting or specified focus in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

xffffff

-0.68

CBA

-0.61

disposed

-0.56

 ProgressDialog

-0.56

cups

-0.54

 dysplasia

-0.53

 horen

-0.53

diers

-0.52

 RELATIONS

-0.52

 fistula

-0.52

POSITIVE LOGITS

 targets

1.67

 TARGET

1.45

 Targets

1.42

TARGET

1.41

 target

1.37

targets

1.36

 Target

1.33

 getTarget

1.30

 targeted

1.27

 targeting

1.26

Activations Density 0.030%

terms related to targeting or specified focus in various contexts

No Comments

No Known Activations